diff --git a/fastNLP/io/pipe/classification.py b/fastNLP/io/pipe/classification.py
index 450c2058..b1d150aa 100644
--- a/fastNLP/io/pipe/classification.py
+++ b/fastNLP/io/pipe/classification.py
@@ -10,6 +10,7 @@ __all__ = [
]
import re
+import warnings
from nltk import Tree
@@ -22,6 +23,7 @@ from ...core.const import Const
from ...core.dataset import DataSet
from ...core.instance import Instance
from ...core.vocabulary import Vocabulary
+from ...core._logger import logger
nonalpnum = re.compile('[^0-9a-zA-Z?!\']+')
@@ -373,7 +375,17 @@ class SST2Pipe(_CLSPipe):
src_vocab.index_dataset(*data_bundle.datasets.values(), field_name=Const.INPUT)
tgt_vocab = Vocabulary(unknown=None, padding=None)
- tgt_vocab.from_dataset(data_bundle.datasets['train'], field_name=Const.TARGET)
+ tgt_vocab.from_dataset(*[ds for name, ds in data_bundle.iter_datasets() if 'train' in name],
+ field_name=Const.TARGET,
+ no_create_entry_dataset=[ds for name, ds in data_bundle.iter_datasets()
+ if ('train' not in name) and (ds.has_field(Const.TARGET))]
+ )
+ if len(tgt_vocab._no_create_word) > 0:
+ warn_msg = f"There are {len(tgt_vocab._no_create_word)} target labels" \
+ f" in {[name for name in data_bundle.datasets.keys() if 'train' not in name]} " \
+ f"data set but not in train data set!."
+ warnings.warn(warn_msg)
+ logger.warn(warn_msg)
datasets = []
for name, dataset in data_bundle.datasets.items():
if dataset.has_field(Const.TARGET):
diff --git a/fastNLP/io/pipe/matching.py b/fastNLP/io/pipe/matching.py
index 3db79aef..7620a556 100644
--- a/fastNLP/io/pipe/matching.py
+++ b/fastNLP/io/pipe/matching.py
@@ -15,11 +15,14 @@ __all__ = [
"MNLIPipe",
]
+import warnings
+
from .pipe import Pipe
from .utils import get_tokenizer
from ..loader.matching import SNLILoader, MNLILoader, QNLILoader, RTELoader, QuoraLoader
from ...core.const import Const
from ...core.vocabulary import Vocabulary
+from ...core._logger import logger
class MatchingBertPipe(Pipe):
@@ -101,7 +104,18 @@ class MatchingBertPipe(Pipe):
word_vocab.index_dataset(*data_bundle.datasets.values(), field_name=Const.INPUT)
target_vocab = Vocabulary(padding=None, unknown=None)
- target_vocab.from_dataset(data_bundle.datasets['train'], field_name=Const.TARGET)
+ target_vocab.from_dataset(*[ds for name, ds in data_bundle.iter_datasets() if 'train' in name],
+ field_name=Const.TARGET,
+ no_create_entry_dataset=[ds for name, ds in data_bundle.iter_datasets()
+ if ('train' not in name) and (ds.has_field(Const.TARGET))]
+ )
+ if len(target_vocab._no_create_word) > 0:
+ warn_msg = f"There are {len(tgt_vocab._no_create_word)} target labels" \
+ f" in {[name for name in data_bundle.datasets.keys() if 'train' not in name]} " \
+ f"data set but not in train data set!."
+ warnings.warn(warn_msg)
+ logger.warn(warn_msg)
+
has_target_datasets = [dataset for name, dataset in data_bundle.datasets.items() if
dataset.has_field(Const.TARGET)]
target_vocab.index_dataset(*has_target_datasets, field_name=Const.TARGET)
@@ -227,7 +241,18 @@ class MatchingPipe(Pipe):
word_vocab.index_dataset(*data_bundle.datasets.values(), field_name=[Const.INPUTS(0), Const.INPUTS(1)])
target_vocab = Vocabulary(padding=None, unknown=None)
- target_vocab.from_dataset(data_bundle.datasets['train'], field_name=Const.TARGET)
+ target_vocab.from_dataset(*[ds for name, ds in data_bundle.iter_datasets() if 'train' in name],
+ field_name=Const.TARGET,
+ no_create_entry_dataset=[ds for name, ds in data_bundle.iter_datasets()
+ if ('train' not in name) and (ds.has_field(Const.TARGET))]
+ )
+ if len(target_vocab._no_create_word) > 0:
+ warn_msg = f"There are {len(tgt_vocab._no_create_word)} target labels" \
+ f" in {[name for name in data_bundle.datasets.keys() if 'train' not in name]} " \
+ f"data set but not in train data set!."
+ warnings.warn(warn_msg)
+ logger.warn(warn_msg)
+
has_target_datasets = [dataset for name, dataset in data_bundle.datasets.items() if
dataset.has_field(Const.TARGET)]
target_vocab.index_dataset(*has_target_datasets, field_name=Const.TARGET)
diff --git a/fastNLP/io/pipe/utils.py b/fastNLP/io/pipe/utils.py
index ea7e0aa8..3db9c4fe 100644
--- a/fastNLP/io/pipe/utils.py
+++ b/fastNLP/io/pipe/utils.py
@@ -7,9 +7,11 @@ __all__ = [
]
from typing import List
+import warnings
from ...core.const import Const
from ...core.vocabulary import Vocabulary
+from ...core._logger import logger
def iob2(tags: List[str]) -> List[str]:
@@ -111,7 +113,17 @@ def _indexize(data_bundle, input_field_names=Const.INPUT, target_field_names=Con
for target_field_name in target_field_names:
tgt_vocab = Vocabulary(unknown=None, padding=None)
- tgt_vocab.from_dataset(data_bundle.datasets['train'], field_name=target_field_name)
+ tgt_vocab.from_dataset(*[ds for name, ds in data_bundle.iter_datasets() if 'train' in name],
+ field_name=Const.TARGET,
+ no_create_entry_dataset=[ds for name, ds in data_bundle.iter_datasets()
+ if ('train' not in name) and (ds.has_field(Const.TARGET))]
+ )
+ if len(tgt_vocab._no_create_word) > 0:
+ warn_msg = f"There are {len(tgt_vocab._no_create_word)} target labels" \
+ f" in {[name for name in data_bundle.datasets.keys() if 'train' not in name]} " \
+ f"data set but not in train data set!."
+ warnings.warn(warn_msg)
+ logger.warn(warn_msg)
tgt_vocab.index_dataset(*data_bundle.datasets.values(), field_name=target_field_name)
data_bundle.set_vocab(tgt_vocab, target_field_name)
diff --git a/test/data_for_tests/io/MNLI/dev_matched.tsv b/test/data_for_tests/io/MNLI/dev_matched.tsv
new file mode 100755
index 00000000..ace2dd27
--- /dev/null
+++ b/test/data_for_tests/io/MNLI/dev_matched.tsv
@@ -0,0 +1,6 @@
+index promptID pairID genre sentence1_binary_parse sentence2_binary_parse sentence1_parse sentence2_parse sentence1 sentence2 label1 label2 label3 label4 label5 gold_label
+0 63735 63735n slate ( ( The ( new rights ) ) ( are ( nice enough ) ) ) ( Everyone ( really ( likes ( the ( newest benefits ) ) ) ) ) (ROOT (S (NP (DT The) (JJ new) (NNS rights)) (VP (VBP are) (ADJP (JJ nice) (RB enough))))) (ROOT (S (NP (NN Everyone)) (VP (ADVP (RB really)) (VBZ likes) (NP (DT the) (JJS newest) (NNS benefits))))) The new rights are nice enough Everyone really likes the newest benefits neutral entailment neutral neutral neutral neutral
+1 91383 91383c government ( ( This site ) ( ( includes ( ( ( ( a list ) ( of ( all ( award winners ) ) ) ) and ) ( ( a ( searchable database ) ) ( of ( Government ( Executive articles ) ) ) ) ) ) . ) ) ( ( ( The ( Government ( Executive articles ) ) ) ( housed ( on ( the website ) ) ) ) ( ( ( are not ) ( able ( to ( be searched ) ) ) ) . ) ) (ROOT (S (NP (DT This) (NN site)) (VP (VBZ includes) (NP (NP (NP (DT a) (NN list)) (PP (IN of) (NP (DT all) (NN award) (NNS winners)))) (CC and) (NP (NP (DT a) (JJ searchable) (NN database)) (PP (IN of) (NP (NNP Government) (NNP Executive) (NNS articles)))))) (. .))) (ROOT (S (NP (NP (DT The) (NNP Government) (NNP Executive) (NNS articles)) (VP (VBN housed) (PP (IN on) (NP (DT the) (NN website))))) (VP (VBP are) (RB not) (ADJP (JJ able) (S (VP (TO to) (VP (VB be) (ADJP (JJ searched))))))) (. .))) This site includes a list of all award winners and a searchable database of Government Executive articles. The Government Executive articles housed on the website are not able to be searched. contradiction contradiction contradiction contradiction contradiction contradiction
+2 755 755e telephone ( ( ( ( uh ( i ( ( do n't ) ( know ( ( i i ) ( have ( ( mixed emotions ) ( about ( him ( ( uh sometimes ) ( i ( like him ) ) ) ) ) ) ) ) ) ) ) ) but ) ( ( at ( the ( same times ) ) ) ( i ( love ( to ( see somebody ) ) ) ) ) ) ( beat him ) ) ( I ( ( ( ( ( ( like him ) ( for ( the ( most part ) ) ) ) , ) but ) ( ( would still ) ( enjoy ( seeing ( someone ( beat him ) ) ) ) ) ) . ) ) (ROOT (SINV (S (S (INTJ (UH uh)) (NP (FW i)) (VP (VBP do) (RB n't) (VP (VB know) (NP (NP (FW i) (FW i)) (SBAR (S (VP (VBP have) (VP (VBN mixed) (NP (NNS emotions)) (PP (IN about) (S (NP (PRP him)) (VP (VBG uh) (ADVP (RB sometimes)) (NP (NP (FW i)) (PP (IN like) (NP (PRP him))))))))))))))) (CC but) (S (PP (IN at) (NP (DT the) (JJ same) (NNS times))) (NP (FW i)) (VP (VBP love) (S (VP (TO to) (VP (VB see) (NP (NN somebody)))))))) (VP (VBD beat)) (NP (PRP him)))) (ROOT (S (NP (PRP I)) (VP (VP (VBP like) (NP (PRP him)) (PP (IN for) (NP (DT the) (JJS most) (NN part)))) (, ,) (CC but) (VP (MD would) (ADVP (RB still)) (VP (VB enjoy) (S (VP (VBG seeing) (S (NP (NN someone)) (VP (VB beat) (NP (PRP him))))))))) (. .))) uh i don't know i i have mixed emotions about him uh sometimes i like him but at the same times i love to see somebody beat him I like him for the most part, but would still enjoy seeing someone beat him. entailment entailment entailment entailment entailment entailment
+3 78013 78013c telephone ( yeah ( ( i i ) ( think ( ( my ( favorite restaurant ) ) ( ( is always ) ( been ( ( the ( one closest ) ) ( you ( ( know ( the closest ) ) ( ( as long ) ( as ( it ( 's ( it ( meets ( ( the ( minimum criteria ) ) ( you ( know ( of ( good food ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ( ( My ( favorite restaurants ) ) ( ( ( ( are always ) ( ( ( ( ( at least ) a ) hundred ) miles ) away ) ) ( from ( my house ) ) ) . ) ) (ROOT (S (VP (VB yeah) (NP (NP (FW i) (FW i)) (SBAR (S (VP (VBP think) (SBAR (S (NP (PRP$ my) (JJ favorite) (NN restaurant)) (VP (VBZ is) (ADVP (RB always)) (VP (VBN been) (NP (NP (DT the) (CD one) (JJS closest)) (SBAR (S (NP (PRP you)) (VP (VBP know) (NP (DT the) (JJS closest)) (ADVP (ADVP (RB as) (RB long)) (SBAR (IN as) (S (NP (PRP it)) (VP (VBZ 's) (SBAR (S (NP (PRP it)) (VP (VBZ meets) (NP (NP (DT the) (JJ minimum) (NNS criteria)) (SBAR (S (NP (PRP you)) (VP (VBP know) (PP (IN of) (NP (JJ good) (NN food))))))))))))))))))))))))))))) (ROOT (S (NP (PRP$ My) (JJ favorite) (NNS restaurants)) (VP (VBP are) (ADVP (RB always)) (ADVP (NP (QP (IN at) (JJS least) (DT a) (CD hundred)) (NNS miles)) (RB away)) (PP (IN from) (NP (PRP$ my) (NN house)))) (. .))) yeah i i think my favorite restaurant is always been the one closest you know the closest as long as it's it meets the minimum criteria you know of good food My favorite restaurants are always at least a hundred miles away from my house. contradiction contradiction contradiction contradiction contradiction contradiction
+4 96377 96377c telephone ( i ( ( do n't ) ( know ( um ( do ( you ( do ( ( a lot ) ( of camping ) ) ) ) ) ) ) ) ) ( I ( ( know exactly ) . ) ) (ROOT (S (NP (FW i)) (VP (VBP do) (RB n't) (VP (VB know) (SBAR (S (NP (NN um)) (VP (VBP do) (SBAR (S (NP (PRP you)) (VP (VBP do) (NP (NP (DT a) (NN lot)) (PP (IN of) (NP (NN camping)))))))))))))) (ROOT (S (NP (PRP I)) (VP (VBP know) (ADVP (RB exactly))) (. .))) i don't know um do you do a lot of camping I know exactly. contradiction contradiction contradiction contradiction contradiction contradiction
diff --git a/test/data_for_tests/io/MNLI/dev_mismatched.tsv b/test/data_for_tests/io/MNLI/dev_mismatched.tsv
new file mode 100755
index 00000000..a1da8897
--- /dev/null
+++ b/test/data_for_tests/io/MNLI/dev_mismatched.tsv
@@ -0,0 +1,6 @@
+index promptID pairID genre sentence1_binary_parse sentence2_binary_parse sentence1_parse sentence2_parse sentence1 sentence2 label1 label2 label3 label4 label5 gold_label
+0 75290 75290c letters ( ( Your contribution ) ( ( helped ( make ( it ( possible ( for ( us ( to ( ( provide ( our students ) ) ( with ( a ( quality education ) ) ) ) ) ) ) ) ) ) ) . ) ) ( ( Your contributions ) ( ( were ( of ( ( no help ) ( with ( ( our ( students ' ) ) education ) ) ) ) ) . ) ) (ROOT (S (NP (PRP$ Your) (NN contribution)) (VP (VBD helped) (VP (VB make) (S (NP (PRP it)) (ADJP (JJ possible)) (SBAR (IN for) (S (NP (PRP us)) (VP (TO to) (VP (VB provide) (NP (PRP$ our) (NNS students)) (PP (IN with) (NP (DT a) (NN quality) (NN education)))))))))) (. .))) (ROOT (S (NP (PRP$ Your) (NNS contributions)) (VP (VBD were) (PP (IN of) (NP (NP (DT no) (NN help)) (PP (IN with) (NP (NP (PRP$ our) (NNS students) (POS ')) (NN education)))))) (. .))) Your contribution helped make it possible for us to provide our students with a quality education. Your contributions were of no help with our students' education. contradiction contradiction contradiction contradiction contradiction contradiction
+1 133794 133794c verbatim ( ( ( ( ( ( The answer ) ( ( ( ( has nothing ) ( to ( do ( with ( their cause ) ) ) ) ) , ) however ) ) , ) but ) ( ( with ( ( ( ( ( ( ( ( the ( simple fact ) ) ( that ( dictionaries ( ( are not ) ( exercises ( in ( bi-unique substitutability ) ) ) ) ) ) ) ; ) ( in ( ( ( other words ) , ) ( if ( ( one ( of ( ( the senses ) ( of run ) ) ) ) ( ( is ` ) ( ( ( ( operate ' ) -LRB- ) ( as ( in ( She ( runs ( an ( engine factory ) ) ) ) ) ) ) -RRB- ) ) ) ) ) ) ) , ) ( that ( ( does not ) ( ( make it ) ( ( valid ( to ( assume ( that ( one ( can ( substitute ( ( operate ( for run ) ) ( in ( We ( ( run ( in ( ( the marathon ) ( every year ) ) ) ) . ) ) ) ) ) ) ) ) ) ) ) ( Although ( ( ( ( recognizing this ) ( as ( ( a shortcoming ) ( of dictionaries ) ) ) ) and ) ( ( ( assigning it ) arbitrarily ) ( to ( what ( , ( ( for ( lack ( of ( a ( better term ) ) ) ) ) ( , ( we ( might ( call ( ( the genius ) ( of ( the language ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) , ) ( might ( seem ( trivial ( to ( the ( casual observer ) ) ) ) ) ) ) ) ( , ( it ( is ( ( a ( valid matter ) ) ( for ( concern ( in ( ( the realm ) ( of lexicology ) ) ) ) ) ) ) ) ) ) ) . ) ( Dictionaries ( ( ( are indeed ) ( exercises ( in ( bi-unique substitutability ) ) ) ) . ) ) (ROOT (S (S (NP (DT The) (NN answer)) (VP (VBZ has) (ADVP (NN nothing)) (S (VP (TO to) (VP (VB do) (PP (IN with) (NP (PRP$ their) (NN cause)))))) (, ,) (ADVP (RB however)))) (, ,) (CC but) (S (SBAR (IN with) (S (NP (NP (DT the) (JJ simple) (NN fact)) (SBAR (IN that) (S (NP (NNS dictionaries)) (VP (VBP are) (RB not) (NP (NP (NNS exercises)) (PP (IN in) (NP (JJ bi-unique) (NN substitutability))))))) (: ;) (PP (IN in) (NP (NP (JJ other) (NNS words)) (, ,) (SBAR (IN if) (S (NP (NP (CD one)) (PP (IN of) (NP (NP (DT the) (NNS senses)) (PP (IN of) (NP (NN run)))))) (VP (VBZ is) (`` `) (VP (VB operate) ('' ') (-LRB- -LRB-) (SBAR (RB as) (IN in) (S (NP (PRP She)) (VP (VBZ runs) (NP (DT an) (NN engine) (NN factory))))) (-RRB- -RRB-))))))) (, ,) (SBAR (WHNP (WDT that)) (S (VP (VBZ does) (RB not) (VP (VB make) (NP (PRP it)) (S (ADJP (JJ valid) (S (VP (TO to) (VP (VB assume) (SBAR (IN that) (S (NP (PRP one)) (VP (MD can) (VP (VB substitute) (VP (VB operate) (PP (IN for) (NP (NN run))) (SBAR (IN in) (S (NP (PRP We)) (VP (VB run) (PP (IN in) (NP (NP (DT the) (NN marathon)) (NP (DT every) (NN year)))) (. .))))))))))))) (SBAR (IN Although) (S (S (VP (VBG recognizing) (NP (DT this)) (PP (IN as) (NP (NP (DT a) (NN shortcoming)) (PP (IN of) (NP (NNS dictionaries))))))) (CC and) (S (VP (VBG assigning) (NP (PRP it)) (ADVP (RB arbitrarily)) (PP (TO to) (SBAR (WHNP (WP what)) (S (, ,) (PP (IN for) (NP (NP (NN lack)) (PP (IN of) (NP (DT a) (JJR better) (NN term))))) (, ,) (NP (PRP we)) (VP (MD might) (VP (VB call) (NP (NP (DT the) (NN genius)) (PP (IN of) (NP (DT the) (NN language)))))))))))))))))) (, ,)) (VP (MD might) (VP (VB seem) (ADJP (JJ trivial) (PP (TO to) (NP (DT the) (JJ casual) (NN observer)))))))) (, ,) (NP (PRP it)) (VP (VBZ is) (NP (NP (DT a) (JJ valid) (NN matter)) (PP (IN for) (NP (NP (NN concern)) (PP (IN in) (NP (NP (DT the) (NN realm)) (PP (IN of) (NP (NN lexicology)))))))))) (. .))) (ROOT (S (NP (NNS Dictionaries)) (VP (VBP are) (ADVP (RB indeed)) (NP (NP (NNS exercises)) (PP (IN in) (NP (JJ bi-unique) (NN substitutability))))) (. .))) The answer has nothing to do with their cause, however, but with the simple fact that dictionaries are not exercises in bi-unique substitutability; in other words, if one of the senses of run is `operate' (as in She runs an engine factory ), that does not make it valid to assume that one can substitute operate for run in We run in the marathon every year . Although recognizing this as a shortcoming of dictionaries and assigning it arbitrarily to what, for lack of a better term, we might call the genius of the language, might seem trivial to the casual observer, it is a valid matter for concern in the realm of lexicology. Dictionaries are indeed exercises in bi-unique substitutability. contradiction contradiction contradiction contradiction contradiction contradiction
+2 3628 3628c verbatim ( We ( ( serve ( ( a ( classic ( Tuscan meal ) ) ) ( that ( includes ( ( a ( Florentine terrine ) ) ( made ( with ( dick ( and ( chicken livers ) ) ) ) ) ) ) ) ) ) . ) ) ( We ( ( serve ( ( a meal ) ( of ( Florentine terrine ) ) ) ) . ) ) (ROOT (S (NP (PRP We)) (VP (VBP serve) (NP (NP (DT a) (JJ classic) (NNP Tuscan) (NN meal)) (SBAR (WHNP (WDT that)) (S (VP (VBZ includes) (NP (NP (DT a) (JJ Florentine) (NN terrine)) (VP (VBN made) (PP (IN with) (NP (NN dick) (CC and) (NN chicken) (NNS livers)))))))))) (. .))) (ROOT (S (NP (PRP We)) (VP (VBP serve) (NP (NP (DT a) (NN meal)) (PP (IN of) (NP (NNP Florentine) (NN terrine))))) (. .))) We serve a classic Tuscan meal that includes a Florentine terrine made with dick and chicken livers. We serve a meal of Florentine terrine. contradiction neutral entailment entailment entailment entailment
+3 89411 89411c letters ( ( ( A ( few months ) ) ago ) ( , ( ( ( ( Carl Newton ) and ) I ) ( ( ( wrote ( a letter ) ) ( asking ( you ( to ( ( consider ( a ( financial contribution ) ) ) ( to ( ( graduate Endodontics ) ( at ( Indiana University ) ) ) ) ) ) ) ) ) . ) ) ) ) ( ( ( ( Carl Newton ) and ) I ) ( ( ( have never ) ( ( had ( any ( other ( previous contact ) ) ) ) ( with you ) ) ) . ) ) (ROOT (S (ADVP (NP (DT A) (JJ few) (NNS months)) (RB ago)) (, ,) (NP (NP (NNP Carl) (NNP Newton)) (CC and) (NP (PRP I))) (VP (VBD wrote) (NP (DT a) (NN letter)) (S (VP (VBG asking) (S (NP (PRP you)) (VP (TO to) (VP (VB consider) (NP (DT a) (JJ financial) (NN contribution)) (PP (TO to) (NP (NP (JJ graduate) (NNS Endodontics)) (PP (IN at) (NP (NNP Indiana) (NNP University))))))))))) (. .))) (ROOT (S (NP (NP (NNP Carl) (NNP Newton)) (CC and) (NP (PRP I))) (VP (VBP have) (ADVP (RB never)) (VP (VBN had) (NP (DT any) (JJ other) (JJ previous) (NN contact)) (PP (IN with) (NP (PRP you))))) (. .))) A few months ago, Carl Newton and I wrote a letter asking you to consider a financial contribution to graduate Endodontics at Indiana University. Carl Newton and I have never had any other previous contact with you. contradiction contradiction contradiction contradiction contradiction contradiction
+4 136158 136158e facetoface ( I ( ( was ( on ( ( this earth ) ( you ( know ( ( , ( ( I ( 've ( lived ( on ( ( this earth ) ( for ( some reason ) ) ) ) ) ) ) , ) ) ( I ( just ( ( do n't ) ( know ( what ( it ( is yet ) ) ) ) ) ) ) ) ) ) ) ) ) . ) ) ( I ( ( ( ( do n't ) yet ) ( ( know ( the reason ) ) ( why ( I ( have ( lived ( on earth ) ) ) ) ) ) ) . ) ) (ROOT (S (NP (PRP I)) (VP (VBD was) (PP (IN on) (NP (NP (DT this) (NN earth)) (SBAR (S (NP (PRP you)) (VP (VBP know) (SBAR (S (PRN (, ,) (S (NP (PRP I)) (VP (VBP 've) (VP (VBN lived) (PP (IN on) (NP (NP (DT this) (NN earth)) (PP (IN for) (NP (DT some) (NN reason)))))))) (, ,)) (NP (PRP I)) (ADVP (RB just)) (VP (VBP do) (RB n't) (VP (VB know) (SBAR (WHNP (WP what)) (S (NP (PRP it)) (VP (VBZ is) (ADVP (RB yet))))))))))))))) (. .))) (ROOT (S (NP (PRP I)) (VP (VBP do) (RB n't) (ADVP (RB yet)) (VP (VB know) (NP (DT the) (NN reason)) (SBAR (WHADVP (WRB why)) (S (NP (PRP I)) (VP (VBP have) (VP (VBN lived) (PP (IN on) (NP (NN earth))))))))) (. .))) I was on this earth you know, I've lived on this earth for some reason, I just don't know what it is yet. I don't yet know the reason why I have lived on earth. entailment entailment entailment entailment entailment entailment
diff --git a/test/data_for_tests/io/MNLI/test_matched.tsv b/test/data_for_tests/io/MNLI/test_matched.tsv
new file mode 100755
index 00000000..b90c2d2a
--- /dev/null
+++ b/test/data_for_tests/io/MNLI/test_matched.tsv
@@ -0,0 +1,6 @@
+index promptID pairID genre sentence1_binary_parse sentence2_binary_parse sentence1_parse sentence2_parse sentence1 sentence2
+0 31493 31493 travel ( ( ( ( ( ( ( ( Hierbas , ) ( ans seco ) ) , ) ( ans dulce ) ) , ) and ) frigola ) ( ( ( are just ) ( ( a ( few names ) ) ( worth ( ( keeping ( a look-out ) ) for ) ) ) ) . ) ) ( Hierbas ( ( is ( ( a name ) ( worth ( ( looking out ) for ) ) ) ) . ) ) (ROOT (S (NP (NP (NNS Hierbas)) (, ,) (NP (NN ans) (NN seco)) (, ,) (NP (NN ans) (NN dulce)) (, ,) (CC and) (NP (NN frigola))) (VP (VBP are) (ADVP (RB just)) (NP (NP (DT a) (JJ few) (NNS names)) (PP (JJ worth) (S (VP (VBG keeping) (NP (DT a) (NN look-out)) (PP (IN for))))))) (. .))) (ROOT (S (NP (NNS Hierbas)) (VP (VBZ is) (NP (NP (DT a) (NN name)) (PP (JJ worth) (S (VP (VBG looking) (PRT (RP out)) (PP (IN for))))))) (. .))) Hierbas, ans seco, ans dulce, and frigola are just a few names worth keeping a look-out for. Hierbas is a name worth looking out for.
+1 92164 92164 government ( ( ( The extent ) ( of ( the ( behavioral effects ) ) ) ) ( ( would ( ( depend ( in ( part ( on ( ( the structure ) ( of ( ( ( the ( individual ( account program ) ) ) and ) ( any limits ) ) ) ) ) ) ) ) ( on ( accessing ( the funds ) ) ) ) ) . ) ) ( ( Many people ) ( ( would ( be ( very ( unhappy ( to ( ( loose control ) ( over ( their ( own money ) ) ) ) ) ) ) ) ) . ) ) (ROOT (S (NP (NP (DT The) (NN extent)) (PP (IN of) (NP (DT the) (JJ behavioral) (NNS effects)))) (VP (MD would) (VP (VB depend) (PP (IN in) (NP (NP (NN part)) (PP (IN on) (NP (NP (DT the) (NN structure)) (PP (IN of) (NP (NP (DT the) (JJ individual) (NN account) (NN program)) (CC and) (NP (DT any) (NNS limits)))))))) (PP (IN on) (S (VP (VBG accessing) (NP (DT the) (NNS funds))))))) (. .))) (ROOT (S (NP (JJ Many) (NNS people)) (VP (MD would) (VP (VB be) (ADJP (RB very) (JJ unhappy) (PP (TO to) (NP (NP (JJ loose) (NN control)) (PP (IN over) (NP (PRP$ their) (JJ own) (NN money)))))))) (. .))) The extent of the behavioral effects would depend in part on the structure of the individual account program and any limits on accessing the funds. Many people would be very unhappy to loose control over their own money.
+2 9662 9662 government ( ( ( Timely access ) ( to information ) ) ( ( is ( in ( ( the ( best interests ) ) ( of ( ( ( both GAO ) and ) ( the agencies ) ) ) ) ) ) . ) ) ( It ( ( ( is ( in ( ( everyone 's ) ( best interest ) ) ) ) ( to ( ( have access ) ( to ( information ( in ( a ( timely manner ) ) ) ) ) ) ) ) . ) ) (ROOT (S (NP (NP (JJ Timely) (NN access)) (PP (TO to) (NP (NN information)))) (VP (VBZ is) (PP (IN in) (NP (NP (DT the) (JJS best) (NNS interests)) (PP (IN of) (NP (NP (DT both) (NNP GAO)) (CC and) (NP (DT the) (NNS agencies))))))) (. .))) (ROOT (S (NP (PRP It)) (VP (VBZ is) (PP (IN in) (NP (NP (NN everyone) (POS 's)) (JJS best) (NN interest))) (S (VP (TO to) (VP (VB have) (NP (NN access)) (PP (TO to) (NP (NP (NN information)) (PP (IN in) (NP (DT a) (JJ timely) (NN manner))))))))) (. .))) Timely access to information is in the best interests of both GAO and the agencies. It is in everyone's best interest to have access to information in a timely manner.
+3 5991 5991 travel ( ( Based ( in ( ( the ( Auvergnat ( spa town ) ) ) ( of Vichy ) ) ) ) ( , ( ( the ( French government ) ) ( often ( ( ( ( proved ( more zealous ) ) ( than ( its masters ) ) ) ( in ( ( ( suppressing ( civil liberties ) ) and ) ( ( drawing up ) ( anti-Jewish legislation ) ) ) ) ) . ) ) ) ) ) ( ( The ( French government ) ) ( ( passed ( ( anti-Jewish laws ) ( aimed ( at ( helping ( the Nazi ) ) ) ) ) ) . ) ) (ROOT (S (PP (VBN Based) (PP (IN in) (NP (NP (DT the) (NNP Auvergnat) (NN spa) (NN town)) (PP (IN of) (NP (NNP Vichy)))))) (, ,) (NP (DT the) (JJ French) (NN government)) (ADVP (RB often)) (VP (VBD proved) (NP (JJR more) (NNS zealous)) (PP (IN than) (NP (PRP$ its) (NNS masters))) (PP (IN in) (S (VP (VP (VBG suppressing) (NP (JJ civil) (NNS liberties))) (CC and) (VP (VBG drawing) (PRT (RP up)) (NP (JJ anti-Jewish) (NN legislation))))))) (. .))) (ROOT (S (NP (DT The) (JJ French) (NN government)) (VP (VBD passed) (NP (NP (JJ anti-Jewish) (NNS laws)) (VP (VBN aimed) (PP (IN at) (S (VP (VBG helping) (NP (DT the) (JJ Nazi)))))))) (. .))) Based in the Auvergnat spa town of Vichy, the French government often proved more zealous than its masters in suppressing civil liberties and drawing up anti-Jewish legislation. The French government passed anti-Jewish laws aimed at helping the Nazi.
+4 50156 50156 travel ( ( ( ( ( Built ( in 1870 ) ) ( , ( ( ( its canopy ) ( of ( stained ( glass ( and ( cast iron ) ) ) ) ) ) ( is ( ( the oldest ) ( in Dublin ) ) ) ) ) ) ; ) ( ( its ( enthusiastic ( interior decoration ) ) ) ( ( is also ) ( typical ( of ( the era ) ) ) ) ) ) . ) ( It ( ( ( ( was ( constructed ( in 1870 ) ) ) and ) ( has ( ( the ( oldest canopy ) ) ( in Dublin ) ) ) ) . ) ) (ROOT (S (S (S (VP (VBN Built) (PP (IN in) (NP (CD 1870))))) (, ,) (NP (NP (PRP$ its) (NN canopy)) (PP (IN of) (NP (JJ stained) (NN glass) (CC and) (NN cast) (NN iron)))) (VP (VBZ is) (NP (NP (DT the) (JJS oldest)) (PP (IN in) (NP (NNP Dublin)))))) (: ;) (S (NP (PRP$ its) (JJ enthusiastic) (JJ interior) (NN decoration)) (VP (VBZ is) (ADVP (RB also)) (ADJP (JJ typical) (PP (IN of) (NP (DT the) (NN era)))))) (. .))) (ROOT (S (NP (PRP It)) (VP (VP (VBD was) (VP (VBN constructed) (PP (IN in) (NP (CD 1870))))) (CC and) (VP (VBZ has) (NP (NP (DT the) (JJS oldest) (NN canopy)) (PP (IN in) (NP (NNP Dublin)))))) (. .))) Built in 1870, its canopy of stained glass and cast iron is the oldest in Dublin; its enthusiastic interior decoration is also typical of the era. It was constructed in 1870 and has the oldest canopy in Dublin.
diff --git a/test/data_for_tests/io/MNLI/test_mismatched.tsv b/test/data_for_tests/io/MNLI/test_mismatched.tsv
new file mode 100755
index 00000000..798cd395
--- /dev/null
+++ b/test/data_for_tests/io/MNLI/test_mismatched.tsv
@@ -0,0 +1,6 @@
+index promptID pairID genre sentence1_binary_parse sentence2_binary_parse sentence1_parse sentence2_parse sentence1 sentence2
+0 16130 16130 facetoface ( ( What ( have ( you decided ) ) ) ( , ( what ( ( ( are you ) ( going ( to do ) ) ) ? ) ) ) ) ( So ( what ( ( 's ( your decision ) ) ? ) ) ) (ROOT (SBARQ (SBAR (WHNP (WP What)) (S (VP (VBP have) (S (NP (PRP you)) (VP (VBD decided)))))) (, ,) (WHNP (WP what)) (SQ (VBP are) (NP (PRP you)) (VP (VBG going) (S (VP (TO to) (VP (VB do)))))) (. ?))) (ROOT (SBARQ (RB So) (WHNP (WP what)) (SQ (VBZ 's) (NP (PRP$ your) (NN decision))) (. ?))) What have you decided, what are you going to do? So what's your decision?
+1 128269 128269 oup ( ( ( Women 's ) clothing ) ( ( is ( characterized ( by ( ( great diversity ) ( in ( ( styles and ) ( short ( production runs ) ) ) ) ) ) ) ) . ) ) ( ( ( Men 's ) clothing ) ( typically ( ( ( has ( the ( ( most stylistic ) diversity ) ) ) ( unlike ( ( the blandness ) ( of ( ( women 's ) fashion ) ) ) ) ) . ) ) ) (ROOT (S (NP (NP (NNP Women) (POS 's)) (NN clothing)) (VP (VBZ is) (VP (VBN characterized) (PP (IN by) (NP (NP (JJ great) (NN diversity)) (PP (IN in) (NP (NP (NNS styles)) (CC and) (NP (JJ short) (NN production) (NNS runs)))))))) (. .))) (ROOT (S (NP (NP (NNP Men) (POS 's)) (NN clothing)) (ADVP (RB typically)) (VP (VBZ has) (NP (DT the) (ADJP (RBS most) (JJ stylistic)) (NN diversity)) (PP (IN unlike) (NP (NP (DT the) (NN blandness)) (PP (IN of) (NP (NP (NNS women) (POS 's)) (NN fashion)))))) (. .))) Women's clothing is characterized by great diversity in styles and short production runs. Men's clothing typically has the most stylistic diversity unlike the blandness of women's fashion.
+2 130938 130938 nineeleven ( ( ( ( ( Reports ( from ( ( two ( flight attendants ) ) ( in ( the ( coach cabin ) ) ) ) ) ) , ) ( ( ( Betty Ong ) and ) ( Madeline ( Amy Sweeney ) ) ) ) , ) ( ( ( tell us ) ( ( most ( of what ) ) ( we ( know ( about ( how ( ( the hijacking ) happened ) ) ) ) ) ) ) . ) ) ( ( ( The report ) ( on ( the hijacking ) ) ) ( ( ( was ( ( over ( five hundred ) ) pages ) ) long ) . ) ) (ROOT (S (NP (NP (NP (NNS Reports)) (PP (IN from) (NP (NP (CD two) (NN flight) (NNS attendants)) (PP (IN in) (NP (DT the) (NN coach) (NN cabin)))))) (, ,) (NP (NP (NNP Betty) (NNP Ong)) (CC and) (NP (NNP Madeline) (NNP Amy) (NNP Sweeney))) (, ,)) (VP (VBP tell) (NP (PRP us)) (SBAR (WHNP (JJS most) (WHPP (IN of) (WHNP (WP what)))) (S (NP (PRP we)) (VP (VBP know) (PP (IN about) (SBAR (WHADVP (WRB how)) (S (NP (DT the) (NN hijacking)) (VP (VBD happened))))))))) (. .))) (ROOT (S (NP (NP (DT The) (NN report)) (PP (IN on) (NP (DT the) (NN hijacking)))) (VP (VBD was) (NP (QP (RB over) (CD five) (CD hundred)) (NNS pages)) (ADVP (RB long))) (. .))) Reports from two flight attendants in the coach cabin, Betty Ong and Madeline Amy Sweeney, tell us most of what we know about how the hijacking happened. The report on the hijacking was over five hundred pages long.
+3 40009 40009 nineeleven ( ( At ( about 9:20 ) ) ( , ( ( ( security personnel ) ( at ( FAA headquarters ) ) ) ( ( ( ( set up ) ( a ( hijacking teleconference ) ) ) ( with ( ( ( several agencies ) , ) ( including ( the ( Defense Department ) ) ) ) ) ) . ) ) ) ) ( ( The teleconference ) ( ( lasted ( for ( 13 ( straight hours ) ) ) ) . ) ) (ROOT (S (PP (IN At) (NP (QP (RB about) (CD 9:20)))) (, ,) (NP (NP (NN security) (NNS personnel)) (PP (IN at) (NP (NNP FAA) (NNS headquarters)))) (VP (VBD set) (PRT (RP up)) (NP (DT a) (VBG hijacking) (NN teleconference)) (PP (IN with) (NP (NP (JJ several) (NNS agencies)) (, ,) (PP (VBG including) (NP (DT the) (NNP Defense) (NNP Department)))))) (. .))) (ROOT (S (NP (DT The) (NN teleconference)) (VP (VBD lasted) (PP (IN for) (NP (CD 13) (JJ straight) (NNS hours)))) (. .))) At about 9:20, security personnel at FAA headquarters set up a hijacking teleconference with several agencies, including the Defense Department. The teleconference lasted for 13 straight hours.
+4 105266 105266 nineeleven ( So ( we ( ( 've ( ( got ( ( a couple ) ( of aircraft ) ) ) ( ( up there ) ( that ( ( have ( those instructions ) ) ( at ( this ( present time ) ) ) ) ) ) ) ) ? ) ) ) ( ( At ( the ( present time ) ) ) ( , ( there ( ( ( ( ( were n't ) ( ( any aircraft ) ( in ( the air ) ) ) ) , ) right ) ? ) ) ) ) (ROOT (S (IN So) (NP (PRP we)) (VP (VBP 've) (VP (VBD got) (NP (NP (DT a) (NN couple)) (PP (IN of) (NP (NN aircraft)))) (ADVP (ADVP (RB up) (RB there)) (SBAR (WHNP (WDT that)) (S (VP (VBP have) (NP (DT those) (NNS instructions)) (PP (IN at) (NP (DT this) (JJ present) (NN time))))))))) (. ?))) (ROOT (S (PP (IN At) (NP (DT the) (JJ present) (NN time))) (, ,) (NP (EX there)) (VP (VBD were) (RB n't) (NP (NP (DT any) (NN aircraft)) (PP (IN in) (NP (DT the) (NN air)))) (, ,) (ADJP (JJ right))) (. ?))) So we've got a couple of aircraft up there that have those instructions at this present time? At the present time, there weren't any aircraft in the air, right?
diff --git a/test/data_for_tests/io/MNLI/train.tsv b/test/data_for_tests/io/MNLI/train.tsv
new file mode 100755
index 00000000..4ceebefd
--- /dev/null
+++ b/test/data_for_tests/io/MNLI/train.tsv
@@ -0,0 +1,7 @@
+index promptID pairID genre sentence1_binary_parse sentence2_binary_parse sentence1_parse sentence2_parse sentence1 sentence2 label1 gold_label
+0 31193 31193n government ( ( Conceptually ( cream skimming ) ) ( ( has ( ( ( two ( basic dimensions ) ) - ) ( ( product and ) geography ) ) ) . ) ) ( ( ( Product and ) geography ) ( ( are ( what ( make ( cream ( skimming work ) ) ) ) ) . ) ) (ROOT (S (NP (JJ Conceptually) (NN cream) (NN skimming)) (VP (VBZ has) (NP (NP (CD two) (JJ basic) (NNS dimensions)) (: -) (NP (NN product) (CC and) (NN geography)))) (. .))) (ROOT (S (NP (NN Product) (CC and) (NN geography)) (VP (VBP are) (SBAR (WHNP (WP what)) (S (VP (VBP make) (NP (NP (NN cream)) (VP (VBG skimming) (NP (NN work)))))))) (. .))) Conceptually cream skimming has two basic dimensions - product and geography. Product and geography are what make cream skimming work. neutral neutral
+1 101457 101457e telephone ( you ( ( know ( during ( ( ( the season ) and ) ( i guess ) ) ) ) ( at ( at ( ( your level ) ( uh ( you ( ( ( lose them ) ( to ( the ( next level ) ) ) ) ( if ( ( if ( they ( decide ( to ( recall ( the ( the ( parent team ) ) ) ) ) ) ) ) ( ( the Braves ) ( decide ( to ( call ( to ( ( recall ( a guy ) ) ( from ( ( triple A ) ( ( ( then ( ( a ( double ( A guy ) ) ) ( ( goes up ) ( to ( replace him ) ) ) ) ) and ) ( ( a ( single ( A guy ) ) ) ( ( goes up ) ( to ( replace him ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ( You ( ( ( ( lose ( the things ) ) ( to ( the ( following level ) ) ) ) ( if ( ( the people ) recall ) ) ) . ) ) (ROOT (S (NP (PRP you)) (VP (VBP know) (PP (IN during) (NP (NP (DT the) (NN season)) (CC and) (NP (FW i) (FW guess)))) (PP (IN at) (IN at) (NP (NP (PRP$ your) (NN level)) (SBAR (S (INTJ (UH uh)) (NP (PRP you)) (VP (VBP lose) (NP (PRP them)) (PP (TO to) (NP (DT the) (JJ next) (NN level))) (SBAR (IN if) (S (SBAR (IN if) (S (NP (PRP they)) (VP (VBP decide) (S (VP (TO to) (VP (VB recall) (NP (DT the) (DT the) (NN parent) (NN team)))))))) (NP (DT the) (NNPS Braves)) (VP (VBP decide) (S (VP (TO to) (VP (VB call) (S (VP (TO to) (VP (VB recall) (NP (DT a) (NN guy)) (PP (IN from) (NP (NP (RB triple) (DT A)) (SBAR (S (S (ADVP (RB then)) (NP (DT a) (JJ double) (NNP A) (NN guy)) (VP (VBZ goes) (PRT (RP up)) (S (VP (TO to) (VP (VB replace) (NP (PRP him))))))) (CC and) (S (NP (DT a) (JJ single) (NNP A) (NN guy)) (VP (VBZ goes) (PRT (RP up)) (S (VP (TO to) (VP (VB replace) (NP (PRP him)))))))))))))))))))))))))))) (ROOT (S (NP (PRP You)) (VP (VBP lose) (NP (DT the) (NNS things)) (PP (TO to) (NP (DT the) (JJ following) (NN level))) (SBAR (IN if) (S (NP (DT the) (NNS people)) (VP (VBP recall))))) (. .))) you know during the season and i guess at at your level uh you lose them to the next level if if they decide to recall the the parent team the Braves decide to call to recall a guy from triple A then a double A guy goes up to replace him and a single A guy goes up to replace him You lose the things to the following level if the people recall. entailment entailment
+2 134793 134793e fiction ( ( One ( of ( our number ) ) ) ( ( will ( ( ( carry out ) ( your instructions ) ) minutely ) ) . ) ) ( ( ( A member ) ( of ( my team ) ) ) ( ( will ( ( execute ( your orders ) ) ( with ( immense precision ) ) ) ) . ) ) (ROOT (S (NP (NP (CD One)) (PP (IN of) (NP (PRP$ our) (NN number)))) (VP (MD will) (VP (VB carry) (PRT (RP out)) (NP (PRP$ your) (NNS instructions)) (ADVP (RB minutely)))) (. .))) (ROOT (S (NP (NP (DT A) (NN member)) (PP (IN of) (NP (PRP$ my) (NN team)))) (VP (MD will) (VP (VB execute) (NP (PRP$ your) (NNS orders)) (PP (IN with) (NP (JJ immense) (NN precision))))) (. .))) One of our number will carry out your instructions minutely. A member of my team will execute your orders with immense precision. entailment entailment
+3 37397 37397e fiction ( ( How ( ( ( do you ) know ) ? ) ) ( ( All this ) ( ( ( is ( their information ) ) again ) . ) ) ) ( ( This information ) ( ( belongs ( to them ) ) . ) ) (ROOT (S (SBARQ (WHADVP (WRB How)) (SQ (VBP do) (NP (PRP you)) (VP (VB know))) (. ?)) (NP (PDT All) (DT this)) (VP (VBZ is) (NP (PRP$ their) (NN information)) (ADVP (RB again))) (. .))) (ROOT (S (NP (DT This) (NN information)) (VP (VBZ belongs) (PP (TO to) (NP (PRP them)))) (. .))) How do you know? All this is their information again. This information belongs to them. entailment entailment
+4 50563 50563n telephone ( yeah ( i ( ( tell you ) ( what ( ( though ( if ( you ( go ( price ( some ( of ( those ( tennis shoes ) ) ) ) ) ) ) ) ) ( i ( can ( see ( why ( now ( you ( know ( they ( 're ( ( getting up ) ( in ( the ( hundred ( dollar range ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ( ( The ( tennis shoes ) ) ( ( have ( ( a range ) ( of prices ) ) ) . ) ) (ROOT (S (VP (VB yeah) (S (NP (FW i)) (VP (VB tell) (NP (PRP you)) (SBAR (WHNP (WP what)) (S (SBAR (RB though) (IN if) (S (NP (PRP you)) (VP (VBP go) (VP (VB price) (NP (NP (DT some)) (PP (IN of) (NP (DT those) (NN tennis) (NNS shoes)))))))) (NP (FW i)) (VP (MD can) (VP (VB see) (SBAR (WHADVP (WRB why)) (S (ADVP (RB now)) (NP (PRP you)) (VP (VBP know) (SBAR (S (NP (PRP they)) (VP (VBP 're) (VP (VBG getting) (PRT (RP up)) (PP (IN in) (NP (DT the) (CD hundred) (NN dollar) (NN range))))))))))))))))))) (ROOT (S (NP (DT The) (NN tennis) (NNS shoes)) (VP (VBP have) (NP (NP (DT a) (NN range)) (PP (IN of) (NP (NNS prices))))) (. .))) yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range The tennis shoes have a range of prices. neutral neutral
+11 11877 11877c travel ( ( Fun ( for ( ( adults and ) children ) ) ) . ) ( ( Fun ( for ( only children ) ) ) . ) (ROOT (S (VP (VB Fun) (PP (IN for) (NP (NNS adults) (CC and) (NNS children)))) (. .))) (ROOT (S (VP (VB Fun) (PP (IN for) (NP (JJ only) (NNS children)))) (. .))) Fun for adults and children. Fun for only children. contradiction contradiction
diff --git a/test/data_for_tests/io/QNLI/dev.tsv b/test/data_for_tests/io/QNLI/dev.tsv
new file mode 100755
index 00000000..ac4ecabe
--- /dev/null
+++ b/test/data_for_tests/io/QNLI/dev.tsv
@@ -0,0 +1,6 @@
+index question sentence label
+0 What came into force after the new constitution was herald? As of that day, the new constitution heralding the Second Republic came into force. entailment
+1 What is the first major city in the stream of the Rhine? The most important tributaries in this area are the Ill below of Strasbourg, the Neckar in Mannheim and the Main across from Mainz. not_entailment
+2 What is the minimum required if you want to teach in Canada? In most provinces a second Bachelor's Degree such as a Bachelor of Education is required to become a qualified teacher. not_entailment
+3 How was Temüjin kept imprisoned by the Tayichi'ud? The Tayichi'ud enslaved Temüjin (reportedly with a cangue, a sort of portable stocks), but with the help of a sympathetic guard, the father of Chilaun (who later became a general of Genghis Khan), he was able to escape from the ger (yurt) in the middle of the night by hiding in a river crevice.[citation needed] entailment
+4 What did Herr Gott, dich loben wir become known as ? He paraphrased the Te Deum as "Herr Gott, dich loben wir" with a simplified form of the melody. not_entailment
diff --git a/test/data_for_tests/io/QNLI/test.tsv b/test/data_for_tests/io/QNLI/test.tsv
new file mode 100755
index 00000000..55bfbeaa
--- /dev/null
+++ b/test/data_for_tests/io/QNLI/test.tsv
@@ -0,0 +1,6 @@
+index question sentence
+0 What organization is devoted to Jihad against Israel? For some decades prior to the First Palestine Intifada in 1987, the Muslim Brotherhood in Palestine took a "quiescent" stance towards Israel, focusing on preaching, education and social services, and benefiting from Israel's "indulgence" to build up a network of mosques and charitable organizations.
+1 In what century was the Yarrow-Schlick-Tweedy balancing system used? In the late 19th century, the Yarrow-Schlick-Tweedy balancing 'system' was used on some marine triple expansion engines.
+2 The largest brand of what store in the UK is located in Kingston Park? Close to Newcastle, the largest indoor shopping centre in Europe, the MetroCentre, is located in Gateshead.
+3 What does the IPCC rely on for research? In principle, this means that any significant new evidence or events that change our understanding of climate science between this deadline and publication of an IPCC report cannot be included.
+4 What is the principle about relating spin and space variables? Thus in the case of two fermions there is a strictly negative correlation between spatial and spin variables, whereas for two bosons (e.g. quanta of electromagnetic waves, photons) the correlation is strictly positive.
diff --git a/test/data_for_tests/io/QNLI/train.tsv b/test/data_for_tests/io/QNLI/train.tsv
new file mode 100755
index 00000000..fc0b966e
--- /dev/null
+++ b/test/data_for_tests/io/QNLI/train.tsv
@@ -0,0 +1,6 @@
+index question sentence label
+0 When did the third Digimon series begin? Unlike the two seasons before it and most of the seasons that followed, Digimon Tamers takes a darker and more realistic approach to its story featuring Digimon who do not reincarnate after their deaths and more complex character development in the original Japanese. not_entailment
+1 Which missile batteries often have individual launchers several kilometres from one another? When MANPADS is operated by specialists, batteries may have several dozen teams deploying separately in small sections; self-propelled air defence guns may deploy in pairs. not_entailment
+2 What two things does Popper argue Tarski's theory involves in an evaluation of truth? He bases this interpretation on the fact that examples such as the one described above refer to two things: assertions and the facts to which they refer. entailment
+3 What is the name of the village 9 miles north of Calafat where the Ottoman forces attacked the Russians? On 31 December 1853, the Ottoman forces at Calafat moved against the Russian force at Chetatea or Cetate, a small village nine miles north of Calafat, and engaged them on 6 January 1854. entailment
+4 What famous palace is located in London? London contains four World Heritage Sites: the Tower of London; Kew Gardens; the site comprising the Palace of Westminster, Westminster Abbey, and St Margaret's Church; and the historic settlement of Greenwich (in which the Royal Observatory, Greenwich marks the Prime Meridian, 0° longitude, and GMT). not_entailment
diff --git a/test/data_for_tests/io/RTE/dev.tsv b/test/data_for_tests/io/RTE/dev.tsv
new file mode 100644
index 00000000..f8f72536
--- /dev/null
+++ b/test/data_for_tests/io/RTE/dev.tsv
@@ -0,0 +1,6 @@
+index sentence1 sentence2 label
+0 Dana Reeve, the widow of the actor Christopher Reeve, has died of lung cancer at age 44, according to the Christopher Reeve Foundation. Christopher Reeve had an accident. not_entailment
+1 Yet, we now are discovering that antibiotics are losing their effectiveness against illness. Disease-causing bacteria are mutating faster than we can come up with new antibiotics to fight the new variations. Bacteria is winning the war against antibiotics. entailment
+2 Cairo is now home to some 15 million people - a burgeoning population that produces approximately 10,000 tonnes of rubbish per day, putting an enormous strain on public services. In the past 10 years, the government has tried hard to encourage private investment in the refuse sector, but some estimate 4,000 tonnes of waste is left behind every day, festering in the heat as it waits for someone to clear it up. It is often the people in the poorest neighbourhoods that are worst affected. But in some areas they are fighting back. In Shubra, one of the northern districts of the city, the residents have taken to the streets armed with dustpans and brushes to clean up public areas which have been used as public dumps. 15 million tonnes of rubbish are produced daily in Cairo. not_entailment
+3 The Amish community in Pennsylvania, which numbers about 55,000, lives an agrarian lifestyle, shunning technological advances like electricity and automobiles. And many say their insular lifestyle gives them a sense that they are protected from the violence of American society. But as residents gathered near the school, some wearing traditional garb and arriving in horse-drawn buggies, they said that sense of safety had been shattered. "If someone snaps and wants to do something stupid, there's no distance that's going to stop them," said Jake King, 56, an Amish lantern maker who knew several families whose children had been shot. Pennsylvania has the biggest Amish community in the U.S. not_entailment
+4 Security forces were on high alert after an election campaign in which more than 1,000 people, including seven election candidates, have been killed. Security forces were on high alert after a campaign marred by violence. entailment
diff --git a/test/data_for_tests/io/RTE/test.tsv b/test/data_for_tests/io/RTE/test.tsv
new file mode 100644
index 00000000..e52dfac4
--- /dev/null
+++ b/test/data_for_tests/io/RTE/test.tsv
@@ -0,0 +1,6 @@
+index sentence1 sentence2
+0 Mangla was summoned after Madhumita's sister Nidhi Shukla, who was the first witness in the case. Shukla is related to Mangla.
+1 Authorities in Brazil say that more than 200 people are being held hostage in a prison in the country's remote, Amazonian-jungle state of Rondonia. Authorities in Brazil hold 200 people as hostage.
+2 A mercenary group faithful to the warmongering policy of former Somozist colonel Enrique Bermudez attacked an IFA truck belonging to the interior ministry at 0900 on 26 March in El Jicote, wounded and killed an interior ministry worker and wounded five others. An interior ministry worker was killed by a mercenary group.
+3 The British ambassador to Egypt, Derek Plumbly, told Reuters on Monday that authorities had compiled the list of 10 based on lists from tour companies and from families whose relatives have not been in contact since the bombings. Derek Plumbly resides in Egypt.
+4 Tibone estimated diamond production at four mines operated by Debswana -- Botswana's 50-50 joint venture with De Beers -- could reach 33 million carats this year. Botswana is a business partner of De Beers.
diff --git a/test/data_for_tests/io/RTE/train.tsv b/test/data_for_tests/io/RTE/train.tsv
new file mode 100644
index 00000000..70e5414f
--- /dev/null
+++ b/test/data_for_tests/io/RTE/train.tsv
@@ -0,0 +1,6 @@
+index sentence1 sentence2 label
+0 No Weapons of Mass Destruction Found in Iraq Yet. Weapons of Mass Destruction Found in Iraq. not_entailment
+1 A place of sorrow, after Pope John Paul II died, became a place of celebration, as Roman Catholic faithful gathered in downtown Chicago to mark the installation of new Pope Benedict XVI. Pope Benedict XVI is the new leader of the Roman Catholic Church. entailment
+2 Herceptin was already approved to treat the sickest breast cancer patients, and the company said, Monday, it will discuss with federal regulators the possibility of prescribing the drug for more breast cancer patients. Herceptin can be used to treat breast cancer. entailment
+3 Judie Vivian, chief executive at ProMedica, a medical service company that helps sustain the 2-year-old Vietnam Heart Institute in Ho Chi Minh City (formerly Saigon), said that so far about 1,500 children have received treatment. The previous name of Ho Chi Minh City was Saigon. entailment
+4 A man is due in court later charged with the murder 26 years ago of a teenager whose case was the first to be featured on BBC One's Crimewatch. Colette Aram, 16, was walking to her boyfriend's house in Keyworth, Nottinghamshire, on 30 October 1983 when she disappeared. Her body was later found in a field close to her home. Paul Stewart Hutchinson, 50, has been charged with murder and is due before Nottingham magistrates later. Paul Stewart Hutchinson is accused of having stabbed a girl. not_entailment
diff --git a/test/data_for_tests/io/SNLI/snli_1.0_dev.jsonl b/test/data_for_tests/io/SNLI/snli_1.0_dev.jsonl
new file mode 100755
index 00000000..2d091c73
--- /dev/null
+++ b/test/data_for_tests/io/SNLI/snli_1.0_dev.jsonl
@@ -0,0 +1,5 @@
+{"annotator_labels": ["neutral", "entailment", "neutral", "neutral", "neutral"], "captionID": "4705552913.jpg#2", "gold_label": "neutral", "pairID": "4705552913.jpg#2r1n", "sentence1": "Two women are embracing while holding to go packages.", "sentence1_binary_parse": "( ( Two women ) ( ( are ( embracing ( while ( holding ( to ( go packages ) ) ) ) ) ) . ) )", "sentence1_parse": "(ROOT (S (NP (CD Two) (NNS women)) (VP (VBP are) (VP (VBG embracing) (SBAR (IN while) (S (NP (VBG holding)) (VP (TO to) (VP (VB go) (NP (NNS packages)))))))) (. .)))", "sentence2": "The sisters are hugging goodbye while holding to go packages after just eating lunch.", "sentence2_binary_parse": "( ( The sisters ) ( ( are ( ( hugging goodbye ) ( while ( holding ( to ( ( go packages ) ( after ( just ( eating lunch ) ) ) ) ) ) ) ) ) . ) )", "sentence2_parse": "(ROOT (S (NP (DT The) (NNS sisters)) (VP (VBP are) (VP (VBG hugging) (NP (UH goodbye)) (PP (IN while) (S (VP (VBG holding) (S (VP (TO to) (VP (VB go) (NP (NNS packages)) (PP (IN after) (S (ADVP (RB just)) (VP (VBG eating) (NP (NN lunch))))))))))))) (. .)))"}
+{"annotator_labels": ["entailment", "entailment", "entailment", "entailment", "entailment"], "captionID": "4705552913.jpg#2", "gold_label": "entailment", "pairID": "4705552913.jpg#2r1e", "sentence1": "Two women are embracing while holding to go packages.", "sentence1_binary_parse": "( ( Two women ) ( ( are ( embracing ( while ( holding ( to ( go packages ) ) ) ) ) ) . ) )", "sentence1_parse": "(ROOT (S (NP (CD Two) (NNS women)) (VP (VBP are) (VP (VBG embracing) (SBAR (IN while) (S (NP (VBG holding)) (VP (TO to) (VP (VB go) (NP (NNS packages)))))))) (. .)))", "sentence2": "Two woman are holding packages.", "sentence2_binary_parse": "( ( Two woman ) ( ( are ( holding packages ) ) . ) )", "sentence2_parse": "(ROOT (S (NP (CD Two) (NN woman)) (VP (VBP are) (VP (VBG holding) (NP (NNS packages)))) (. .)))"}
+{"annotator_labels": ["contradiction", "contradiction", "contradiction", "contradiction", "contradiction"], "captionID": "4705552913.jpg#2", "gold_label": "contradiction", "pairID": "4705552913.jpg#2r1c", "sentence1": "Two women are embracing while holding to go packages.", "sentence1_binary_parse": "( ( Two women ) ( ( are ( embracing ( while ( holding ( to ( go packages ) ) ) ) ) ) . ) )", "sentence1_parse": "(ROOT (S (NP (CD Two) (NNS women)) (VP (VBP are) (VP (VBG embracing) (SBAR (IN while) (S (NP (VBG holding)) (VP (TO to) (VP (VB go) (NP (NNS packages)))))))) (. .)))", "sentence2": "The men are fighting outside a deli.", "sentence2_binary_parse": "( ( The men ) ( ( are ( fighting ( outside ( a deli ) ) ) ) . ) )", "sentence2_parse": "(ROOT (S (NP (DT The) (NNS men)) (VP (VBP are) (VP (VBG fighting) (PP (IN outside) (NP (DT a) (NNS deli))))) (. .)))"}
+{"annotator_labels": ["entailment", "entailment", "entailment", "entailment", "entailment"], "captionID": "2407214681.jpg#0", "gold_label": "entailment", "pairID": "2407214681.jpg#0r1e", "sentence1": "Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.", "sentence1_binary_parse": "( ( ( Two ( young children ) ) ( in ( ( ( ( ( blue jerseys ) , ) ( one ( with ( the ( number 9 ) ) ) ) ) and ) ( one ( with ( the ( number 2 ) ) ) ) ) ) ) ( ( are ( ( ( standing ( on ( ( wooden steps ) ( in ( a bathroom ) ) ) ) ) and ) ( ( washing ( their hands ) ) ( in ( a sink ) ) ) ) ) . ) )", "sentence1_parse": "(ROOT (S (NP (NP (CD Two) (JJ young) (NNS children)) (PP (IN in) (NP (NP (JJ blue) (NNS jerseys)) (, ,) (NP (NP (CD one)) (PP (IN with) (NP (DT the) (NN number) (CD 9)))) (CC and) (NP (NP (CD one)) (PP (IN with) (NP (DT the) (NN number) (CD 2))))))) (VP (VBP are) (VP (VP (VBG standing) (PP (IN on) (NP (NP (JJ wooden) (NNS steps)) (PP (IN in) (NP (DT a) (NN bathroom)))))) (CC and) (VP (VBG washing) (NP (PRP$ their) (NNS hands)) (PP (IN in) (NP (DT a) (NN sink)))))) (. .)))", "sentence2": "Two kids in numbered jerseys wash their hands.", "sentence2_binary_parse": "( ( ( Two kids ) ( in ( numbered jerseys ) ) ) ( ( wash ( their hands ) ) . ) )", "sentence2_parse": "(ROOT (S (NP (NP (CD Two) (NNS kids)) (PP (IN in) (NP (JJ numbered) (NNS jerseys)))) (VP (VBP wash) (NP (PRP$ their) (NNS hands))) (. .)))"}
+{"annotator_labels": ["neutral", "neutral", "neutral", "entailment", "entailment"], "captionID": "2407214681.jpg#0", "gold_label": "neutral", "pairID": "2407214681.jpg#0r1n", "sentence1": "Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.", "sentence1_binary_parse": "( ( ( Two ( young children ) ) ( in ( ( ( ( ( blue jerseys ) , ) ( one ( with ( the ( number 9 ) ) ) ) ) and ) ( one ( with ( the ( number 2 ) ) ) ) ) ) ) ( ( are ( ( ( standing ( on ( ( wooden steps ) ( in ( a bathroom ) ) ) ) ) and ) ( ( washing ( their hands ) ) ( in ( a sink ) ) ) ) ) . ) )", "sentence1_parse": "(ROOT (S (NP (NP (CD Two) (JJ young) (NNS children)) (PP (IN in) (NP (NP (JJ blue) (NNS jerseys)) (, ,) (NP (NP (CD one)) (PP (IN with) (NP (DT the) (NN number) (CD 9)))) (CC and) (NP (NP (CD one)) (PP (IN with) (NP (DT the) (NN number) (CD 2))))))) (VP (VBP are) (VP (VP (VBG standing) (PP (IN on) (NP (NP (JJ wooden) (NNS steps)) (PP (IN in) (NP (DT a) (NN bathroom)))))) (CC and) (VP (VBG washing) (NP (PRP$ their) (NNS hands)) (PP (IN in) (NP (DT a) (NN sink)))))) (. .)))", "sentence2": "Two kids at a ballgame wash their hands.", "sentence2_binary_parse": "( ( ( Two kids ) ( at ( a ballgame ) ) ) ( ( wash ( their hands ) ) . ) )", "sentence2_parse": "(ROOT (S (NP (NP (CD Two) (NNS kids)) (PP (IN at) (NP (DT a) (NN ballgame)))) (VP (VBP wash) (NP (PRP$ their) (NNS hands))) (. .)))"}
diff --git a/test/data_for_tests/io/SNLI/snli_1.0_test.jsonl b/test/data_for_tests/io/SNLI/snli_1.0_test.jsonl
new file mode 100755
index 00000000..49d40720
--- /dev/null
+++ b/test/data_for_tests/io/SNLI/snli_1.0_test.jsonl
@@ -0,0 +1,5 @@
+{"annotator_labels": ["neutral", "contradiction", "contradiction", "neutral", "neutral"], "captionID": "2677109430.jpg#1", "gold_label": "neutral", "pairID": "2677109430.jpg#1r1n", "sentence1": "This church choir sings to the masses as they sing joyous songs from the book at a church.", "sentence1_binary_parse": "( ( This ( church choir ) ) ( ( ( sings ( to ( the masses ) ) ) ( as ( they ( ( sing ( joyous songs ) ) ( from ( ( the book ) ( at ( a church ) ) ) ) ) ) ) ) . ) )", "sentence1_parse": "(ROOT (S (NP (DT This) (NN church) (NN choir)) (VP (VBZ sings) (PP (TO to) (NP (DT the) (NNS masses))) (SBAR (IN as) (S (NP (PRP they)) (VP (VBP sing) (NP (JJ joyous) (NNS songs)) (PP (IN from) (NP (NP (DT the) (NN book)) (PP (IN at) (NP (DT a) (NN church))))))))) (. .)))", "sentence2": "The church has cracks in the ceiling.", "sentence2_binary_parse": "( ( The church ) ( ( has ( cracks ( in ( the ceiling ) ) ) ) . ) )", "sentence2_parse": "(ROOT (S (NP (DT The) (NN church)) (VP (VBZ has) (NP (NP (NNS cracks)) (PP (IN in) (NP (DT the) (NN ceiling))))) (. .)))"}
+{"annotator_labels": ["entailment", "entailment", "entailment", "neutral", "entailment"], "captionID": "2677109430.jpg#1", "gold_label": "entailment", "pairID": "2677109430.jpg#1r1e", "sentence1": "This church choir sings to the masses as they sing joyous songs from the book at a church.", "sentence1_binary_parse": "( ( This ( church choir ) ) ( ( ( sings ( to ( the masses ) ) ) ( as ( they ( ( sing ( joyous songs ) ) ( from ( ( the book ) ( at ( a church ) ) ) ) ) ) ) ) . ) )", "sentence1_parse": "(ROOT (S (NP (DT This) (NN church) (NN choir)) (VP (VBZ sings) (PP (TO to) (NP (DT the) (NNS masses))) (SBAR (IN as) (S (NP (PRP they)) (VP (VBP sing) (NP (JJ joyous) (NNS songs)) (PP (IN from) (NP (NP (DT the) (NN book)) (PP (IN at) (NP (DT a) (NN church))))))))) (. .)))", "sentence2": "The church is filled with song.", "sentence2_binary_parse": "( ( The church ) ( ( is ( filled ( with song ) ) ) . ) )", "sentence2_parse": "(ROOT (S (NP (DT The) (NN church)) (VP (VBZ is) (VP (VBN filled) (PP (IN with) (NP (NN song))))) (. .)))"}
+{"annotator_labels": ["contradiction", "contradiction", "contradiction", "contradiction", "contradiction"], "captionID": "2677109430.jpg#1", "gold_label": "contradiction", "pairID": "2677109430.jpg#1r1c", "sentence1": "This church choir sings to the masses as they sing joyous songs from the book at a church.", "sentence1_binary_parse": "( ( This ( church choir ) ) ( ( ( sings ( to ( the masses ) ) ) ( as ( they ( ( sing ( joyous songs ) ) ( from ( ( the book ) ( at ( a church ) ) ) ) ) ) ) ) . ) )", "sentence1_parse": "(ROOT (S (NP (DT This) (NN church) (NN choir)) (VP (VBZ sings) (PP (TO to) (NP (DT the) (NNS masses))) (SBAR (IN as) (S (NP (PRP they)) (VP (VBP sing) (NP (JJ joyous) (NNS songs)) (PP (IN from) (NP (NP (DT the) (NN book)) (PP (IN at) (NP (DT a) (NN church))))))))) (. .)))", "sentence2": "A choir singing at a baseball game.", "sentence2_binary_parse": "( ( ( A choir ) ( singing ( at ( a ( baseball game ) ) ) ) ) . )", "sentence2_parse": "(ROOT (NP (NP (DT A) (NN choir)) (VP (VBG singing) (PP (IN at) (NP (DT a) (NN baseball) (NN game)))) (. .)))"}
+{"annotator_labels": ["neutral", "neutral", "neutral", "neutral", "neutral"], "captionID": "6160193920.jpg#4", "gold_label": "neutral", "pairID": "6160193920.jpg#4r1n", "sentence1": "A woman with a green headscarf, blue shirt and a very big grin.", "sentence1_binary_parse": "( ( ( A woman ) ( with ( ( ( ( ( a ( green headscarf ) ) , ) ( blue shirt ) ) and ) ( a ( ( very big ) grin ) ) ) ) ) . )", "sentence1_parse": "(ROOT (NP (NP (DT A) (NN woman)) (PP (IN with) (NP (NP (DT a) (JJ green) (NN headscarf)) (, ,) (NP (JJ blue) (NN shirt)) (CC and) (NP (DT a) (ADJP (RB very) (JJ big)) (NN grin)))) (. .)))", "sentence2": "The woman is young.", "sentence2_binary_parse": "( ( The woman ) ( ( is young ) . ) )", "sentence2_parse": "(ROOT (S (NP (DT The) (NN woman)) (VP (VBZ is) (ADJP (JJ young))) (. .)))"}
+{"annotator_labels": ["entailment", "entailment", "contradiction", "entailment", "neutral"], "captionID": "6160193920.jpg#4", "gold_label": "entailment", "pairID": "6160193920.jpg#4r1e", "sentence1": "A woman with a green headscarf, blue shirt and a very big grin.", "sentence1_binary_parse": "( ( ( A woman ) ( with ( ( ( ( ( a ( green headscarf ) ) , ) ( blue shirt ) ) and ) ( a ( ( very big ) grin ) ) ) ) ) . )", "sentence1_parse": "(ROOT (NP (NP (DT A) (NN woman)) (PP (IN with) (NP (NP (DT a) (JJ green) (NN headscarf)) (, ,) (NP (JJ blue) (NN shirt)) (CC and) (NP (DT a) (ADJP (RB very) (JJ big)) (NN grin)))) (. .)))", "sentence2": "The woman is very happy.", "sentence2_binary_parse": "( ( The woman ) ( ( is ( very happy ) ) . ) )", "sentence2_parse": "(ROOT (S (NP (DT The) (NN woman)) (VP (VBZ is) (ADJP (RB very) (JJ happy))) (. .)))"}
diff --git a/test/data_for_tests/io/SNLI/snli_1.0_train.jsonl b/test/data_for_tests/io/SNLI/snli_1.0_train.jsonl
new file mode 100755
index 00000000..8be03c11
--- /dev/null
+++ b/test/data_for_tests/io/SNLI/snli_1.0_train.jsonl
@@ -0,0 +1,5 @@
+{"annotator_labels": ["neutral"], "captionID": "3416050480.jpg#4", "gold_label": "neutral", "pairID": "3416050480.jpg#4r1n", "sentence1": "A person on a horse jumps over a broken down airplane.", "sentence1_binary_parse": "( ( ( A person ) ( on ( a horse ) ) ) ( ( jumps ( over ( a ( broken ( down airplane ) ) ) ) ) . ) )", "sentence1_parse": "(ROOT (S (NP (NP (DT A) (NN person)) (PP (IN on) (NP (DT a) (NN horse)))) (VP (VBZ jumps) (PP (IN over) (NP (DT a) (JJ broken) (JJ down) (NN airplane)))) (. .)))", "sentence2": "A person is training his horse for a competition.", "sentence2_binary_parse": "( ( A person ) ( ( is ( ( training ( his horse ) ) ( for ( a competition ) ) ) ) . ) )", "sentence2_parse": "(ROOT (S (NP (DT A) (NN person)) (VP (VBZ is) (VP (VBG training) (NP (PRP$ his) (NN horse)) (PP (IN for) (NP (DT a) (NN competition))))) (. .)))"}
+{"annotator_labels": ["contradiction"], "captionID": "3416050480.jpg#4", "gold_label": "contradiction", "pairID": "3416050480.jpg#4r1c", "sentence1": "A person on a horse jumps over a broken down airplane.", "sentence1_binary_parse": "( ( ( A person ) ( on ( a horse ) ) ) ( ( jumps ( over ( a ( broken ( down airplane ) ) ) ) ) . ) )", "sentence1_parse": "(ROOT (S (NP (NP (DT A) (NN person)) (PP (IN on) (NP (DT a) (NN horse)))) (VP (VBZ jumps) (PP (IN over) (NP (DT a) (JJ broken) (JJ down) (NN airplane)))) (. .)))", "sentence2": "A person is at a diner, ordering an omelette.", "sentence2_binary_parse": "( ( A person ) ( ( ( ( is ( at ( a diner ) ) ) , ) ( ordering ( an omelette ) ) ) . ) )", "sentence2_parse": "(ROOT (S (NP (DT A) (NN person)) (VP (VBZ is) (PP (IN at) (NP (DT a) (NN diner))) (, ,) (S (VP (VBG ordering) (NP (DT an) (NN omelette))))) (. .)))"}
+{"annotator_labels": ["entailment"], "captionID": "3416050480.jpg#4", "gold_label": "entailment", "pairID": "3416050480.jpg#4r1e", "sentence1": "A person on a horse jumps over a broken down airplane.", "sentence1_binary_parse": "( ( ( A person ) ( on ( a horse ) ) ) ( ( jumps ( over ( a ( broken ( down airplane ) ) ) ) ) . ) )", "sentence1_parse": "(ROOT (S (NP (NP (DT A) (NN person)) (PP (IN on) (NP (DT a) (NN horse)))) (VP (VBZ jumps) (PP (IN over) (NP (DT a) (JJ broken) (JJ down) (NN airplane)))) (. .)))", "sentence2": "A person is outdoors, on a horse.", "sentence2_binary_parse": "( ( A person ) ( ( ( ( is outdoors ) , ) ( on ( a horse ) ) ) . ) )", "sentence2_parse": "(ROOT (S (NP (DT A) (NN person)) (VP (VBZ is) (ADVP (RB outdoors)) (, ,) (PP (IN on) (NP (DT a) (NN horse)))) (. .)))"}
+{"annotator_labels": ["neutral"], "captionID": "2267923837.jpg#2", "gold_label": "neutral", "pairID": "2267923837.jpg#2r1n", "sentence1": "Children smiling and waving at camera", "sentence1_binary_parse": "( Children ( ( ( smiling and ) waving ) ( at camera ) ) )", "sentence1_parse": "(ROOT (NP (S (NP (NNP Children)) (VP (VBG smiling) (CC and) (VBG waving) (PP (IN at) (NP (NN camera)))))))", "sentence2": "They are smiling at their parents", "sentence2_binary_parse": "( They ( are ( smiling ( at ( their parents ) ) ) ) )", "sentence2_parse": "(ROOT (S (NP (PRP They)) (VP (VBP are) (VP (VBG smiling) (PP (IN at) (NP (PRP$ their) (NNS parents)))))))"}
+{"annotator_labels": ["entailment"], "captionID": "2267923837.jpg#2", "gold_label": "entailment", "pairID": "2267923837.jpg#2r1e", "sentence1": "Children smiling and waving at camera", "sentence1_binary_parse": "( Children ( ( ( smiling and ) waving ) ( at camera ) ) )", "sentence1_parse": "(ROOT (NP (S (NP (NNP Children)) (VP (VBG smiling) (CC and) (VBG waving) (PP (IN at) (NP (NN camera)))))))", "sentence2": "There are children present", "sentence2_binary_parse": "( There ( ( are children ) present ) )", "sentence2_parse": "(ROOT (S (NP (EX There)) (VP (VBP are) (NP (NNS children)) (ADVP (RB present)))))"}
diff --git a/test/data_for_tests/io/SST-2/dev.tsv b/test/data_for_tests/io/SST-2/dev.tsv
new file mode 100755
index 00000000..3fec0fa6
--- /dev/null
+++ b/test/data_for_tests/io/SST-2/dev.tsv
@@ -0,0 +1,6 @@
+sentence label
+it 's a charming and often affecting journey . 1
+unflinchingly bleak and desperate 0
+allows us to hope that nolan is poised to embark a major career as a commercial yet inventive filmmaker . 1
+the acting , costumes , music , cinematography and sound are all astounding given the production 's austere locales . 1
+it 's slow -- very , very slow . 0
diff --git a/test/data_for_tests/io/SST-2/test.tsv b/test/data_for_tests/io/SST-2/test.tsv
new file mode 100755
index 00000000..6ad46368
--- /dev/null
+++ b/test/data_for_tests/io/SST-2/test.tsv
@@ -0,0 +1,6 @@
+index sentence
+0 uneasy mishmash of styles and genres .
+1 this film 's relationship to actual tension is the same as what christmas-tree flocking in a spray can is to actual snow : a poor -- if durable -- imitation .
+2 by the end of no such thing the audience , like beatrice , has a watchful affection for the monster .
+3 director rob marshall went out gunning to make a great one .
+4 lathan and diggs have considerable personal charm , and their screen rapport makes the old story seem new .
diff --git a/test/data_for_tests/io/SST-2/train.tsv b/test/data_for_tests/io/SST-2/train.tsv
new file mode 100755
index 00000000..4d7ea56c
--- /dev/null
+++ b/test/data_for_tests/io/SST-2/train.tsv
@@ -0,0 +1,6 @@
+sentence label
+hide new secretions from the parental units 0
+contains no wit , only labored gags 0
+that loves its characters and communicates something rather beautiful about human nature 1
+remains utterly satisfied to remain the same throughout 0
+on the worst revenge-of-the-nerds clichés the filmmakers could dredge up 0
diff --git a/test/data_for_tests/io/SST/dev.txt b/test/data_for_tests/io/SST/dev.txt
new file mode 100755
index 00000000..46fca6bf
--- /dev/null
+++ b/test/data_for_tests/io/SST/dev.txt
@@ -0,0 +1,6 @@
+(3 (2 It) (4 (4 (2 's) (4 (3 (2 a) (4 (3 lovely) (2 film))) (3 (2 with) (4 (3 (3 lovely) (2 performances)) (2 (2 by) (2 (2 (2 Buy) (2 and)) (2 Accorsi))))))) (2 .)))
+(2 (2 (1 No) (2 one)) (1 (1 (2 goes) (2 (1 (2 (2 unindicted) (2 here)) (2 ,)) (2 (2 which) (3 (2 (2 is) (2 probably)) (3 (2 for) (4 (2 the) (4 best))))))) (2 .)))
+(3 (2 And) (4 (3 (2 if) (1 (2 you) (1 (2 (2 (2 're) (1 not)) (2 nearly)) (4 (3 (3 moved) (2 (2 to) (1 tears))) (2 (2 by) (2 (2 (2 a) (2 couple)) (2 (2 of) (2 scenes)))))))) (2 (2 ,) (2 (2 you) (2 (2 (2 've) (1 (2 got) (2 (3 (2 ice) (2 water)) (2 (2 in) (2 (2 your) (2 veins)))))) (2 .))))))
+(4 (4 (2 A) (4 (3 (3 warm) (2 ,)) (3 funny))) (3 (2 ,) (3 (4 (4 engaging) (2 film)) (2 .))))
+(4 (3 (2 Uses) (3 (3 (4 (3 sharp) (4 (3 (4 humor) (2 and)) (2 insight))) (2 (2 into) (3 (2 human) (2 nature)))) (2 (2 to) (2 (2 examine) (2 (2 class) (1 conflict)))))) (2 (2 ,) (2 (2 (2 adolescent) (2 (2 (2 yearning) (2 ,)) (3 (2 (2 the) (2 roots)) (3 (2 of) (2 (2 friendship) (2 (2 and) (2 (2 sexual) (2 identity)))))))) (2 .))))
+(2 (2 (2 Half) (1 (2 (2 (2 (2 (2 Submarine) (2 flick)) (2 ,)) (2 (2 Half) (2 (2 Ghost) (2 Story)))) (2 ,)) (2 (2 All) (2 (2 in) (2 (2 one) (2 criminally)))))) (1 (1 neglected) (2 film)))
diff --git a/test/data_for_tests/io/SST/test.txt b/test/data_for_tests/io/SST/test.txt
new file mode 100755
index 00000000..ebf325d8
--- /dev/null
+++ b/test/data_for_tests/io/SST/test.txt
@@ -0,0 +1,6 @@
+(2 (3 (3 Effective) (2 but)) (1 (1 too-tepid) (2 biopic)))
+(3 (3 (2 If) (3 (2 you) (3 (2 sometimes) (2 (2 like) (3 (2 to) (3 (3 (2 go) (2 (2 to) (2 (2 the) (2 movies)))) (3 (2 to) (3 (2 have) (4 fun))))))))) (2 (2 ,) (2 (2 Wasabi) (3 (3 (2 is) (2 (2 a) (2 (3 good) (2 (2 place) (2 (2 to) (2 start)))))) (2 .)))))
+(4 (4 (4 (3 (2 Emerges) (3 (2 as) (3 (2 something) (3 rare)))) (2 ,)) (4 (2 (2 an) (2 (2 issue) (2 movie))) (3 (2 that) (3 (3 (2 's) (4 (3 (3 (2 so) (4 honest)) (2 and)) (3 (2 keenly) (2 observed)))) (2 (2 that) (2 (2 it) (2 (1 (2 does) (2 n't)) (2 (2 feel) (2 (2 like) (2 one)))))))))) (2 .))
+(2 (2 (2 The) (2 film)) (3 (3 (3 (3 provides) (2 (2 some) (3 (4 great) (2 insight)))) (3 (2 into) (3 (2 (2 the) (2 (2 neurotic) (2 mindset))) (3 (2 of) (2 (2 (2 (2 (2 all) (2 comics)) (2 --)) (2 even)) (3 (2 those) (4 (2 who) (4 (2 have) (4 (2 reached) (4 (4 (2 the) (3 (2 absolute) (2 top))) (2 (2 of) (2 (2 the) (2 game))))))))))))) (2 .)))
+(4 (4 (2 Offers) (3 (3 (2 that) (3 (3 rare) (2 combination))) (2 (2 of) (3 (3 (3 entertainment) (2 and)) (2 education))))) (2 .))
+(3 (2 Perhaps) (4 (2 (1 (1 no) (2 picture)) (2 (2 ever) (2 made))) (3 (3 (2 (2 has) (2 (2 more) (3 literally))) (3 (2 showed) (2 (2 that) (2 (1 (2 (2 the) (1 road)) (1 (2 to) (0 hell))) (3 (2 is) (3 (2 paved) (3 (2 with) (3 (3 good) (2 intentions))))))))) (2 .))))
diff --git a/test/data_for_tests/io/SST/train.txt b/test/data_for_tests/io/SST/train.txt
new file mode 100755
index 00000000..d5296ab0
--- /dev/null
+++ b/test/data_for_tests/io/SST/train.txt
@@ -0,0 +1,6 @@
+(3 (2 (2 The) (2 Rock)) (4 (3 (2 is) (4 (2 destined) (2 (2 (2 (2 (2 to) (2 (2 be) (2 (2 the) (2 (2 21st) (2 (2 (2 Century) (2 's)) (2 (3 new) (2 (2 ``) (2 Conan)))))))) (2 '')) (2 and)) (3 (2 that) (3 (2 he) (3 (2 's) (3 (2 going) (3 (2 to) (4 (3 (2 make) (3 (3 (2 a) (3 splash)) (2 (2 even) (3 greater)))) (2 (2 than) (2 (2 (2 (2 (1 (2 Arnold) (2 Schwarzenegger)) (2 ,)) (2 (2 Jean-Claud) (2 (2 Van) (2 Damme)))) (2 or)) (2 (2 Steven) (2 Segal))))))))))))) (2 .)))
+(4 (4 (4 (2 The) (4 (3 gorgeously) (3 (2 elaborate) (2 continuation)))) (2 (2 (2 of) (2 ``)) (2 (2 The) (2 (2 (2 Lord) (2 (2 of) (2 (2 the) (2 Rings)))) (2 (2 '') (2 trilogy)))))) (2 (3 (2 (2 is) (2 (2 so) (2 huge))) (2 (2 that) (3 (2 (2 (2 a) (2 column)) (2 (2 of) (2 words))) (2 (2 (2 (2 can) (1 not)) (3 adequately)) (2 (2 describe) (2 (3 (2 (2 co-writer\/director) (2 (2 Peter) (3 (2 Jackson) (2 's)))) (3 (2 expanded) (2 vision))) (2 (2 of) (2 (2 (2 J.R.R.) (2 (2 Tolkien) (2 's))) (2 Middle-earth))))))))) (2 .)))
+(3 (3 (2 (2 (2 (2 (2 Singer\/composer) (2 (2 Bryan) (2 Adams))) (2 (2 contributes) (2 (2 (2 a) (2 slew)) (2 (2 of) (2 songs))))) (2 (2 --) (2 (2 (2 (2 a) (2 (2 few) (3 potential))) (2 (2 (2 hits) (2 ,)) (2 (2 (2 a) (2 few)) (1 (1 (2 more) (1 (2 simply) (2 intrusive))) (2 (2 to) (2 (2 the) (2 story))))))) (2 --)))) (2 but)) (3 (4 (2 the) (3 (2 whole) (2 package))) (2 (3 certainly) (3 (2 captures) (2 (1 (2 the) (2 (2 (2 intended) (2 (2 ,) (2 (2 er) (2 ,)))) (3 spirit))) (2 (2 of) (2 (2 the) (2 piece)))))))) (2 .))
+(2 (2 (2 You) (2 (2 'd) (2 (2 think) (2 (2 by) (2 now))))) (2 (2 America) (2 (2 (2 would) (1 (2 have) (2 (2 (2 had) (1 (2 enough) (2 (2 of) (2 (2 plucky) (2 (2 British) (1 eccentrics)))))) (4 (2 with) (4 (3 hearts) (3 (2 of) (3 gold))))))) (2 .))))
+(3 (2 ``) (3 (2 Frailty) (4 (2 '') (3 (4 (3 (2 has) (3 (2 been) (3 (4 (3 (3 written) (3 (2 so) (3 well))) (2 ,)) (2 (2 (2 that) (2 even)) (1 (2 (2 a) (2 simple)) (1 (2 ``) (0 Goddammit))))))) (2 !)) (2 '')))))
+(4 (2 (2 Whether) (2 (2 (2 (2 or) (1 not)) (3 (2 you) (2 (2 're) (3 (3 enlightened) (2 (2 by) (2 (2 any) (2 (2 of) (2 (2 Derrida) (2 's))))))))) (2 (2 lectures) (2 (2 on) (2 (2 ``) (2 (2 (2 (2 (2 (2 the) (2 other)) (2 '')) (2 and)) (2 ``)) (2 (2 the) (2 self)))))))) (3 (2 ,) (3 (2 '') (3 (2 Derrida) (3 (3 (2 is) (4 (2 an) (4 (4 (2 undeniably) (3 (4 (3 fascinating) (2 and)) (4 playful))) (2 fellow)))) (2 .))))))
diff --git a/test/data_for_tests/io/imdb/dev.txt b/test/data_for_tests/io/imdb/dev.txt
index 6b548a0c..423e158b 100644
--- a/test/data_for_tests/io/imdb/dev.txt
+++ b/test/data_for_tests/io/imdb/dev.txt
@@ -1,2 +1,6 @@
-neg It, at all, you have seen when harry met sally, then avoid this one. It will not only make you bang your head on the table as why can't bollywood even make a good remake; but also annoy you with the so called funny moments in it. The charm of the movie is missing. Ranee looks terrible. Saif tries to act like he is one hell of an actor. The plots that have been picked up from the original, don't look effective either. The part where both of them bring their friends along and they hit a note, it just doesn't look appealing. What can be more disastrous? you wanna waste some money, this is what you can get. Otherwise, put some more bucks, and watch the original. Its too good to miss..
-neg The monster from Enemy Mine somehow made his way into a small mountain community, where he has taken up residence. He's being hunted by a female doctor-turned-vigilante who is out to exterminate him. This female assassin, who looks like a refugee from a Motley Crue video, rides around on a motorcycle and tries to save a bunch of kids who have chosen to have a Big Chill weekend right smack dab in the middle of the monster's turf. Decapitations and lots of blood are primarily in place to draw attention away from the story which limps along like a bad version of the Island of Dr. Moreau (and yes, it's worse than the one with Val Kilmer).
+neg You can never have seen either film and still know that The Jerk Too is a disaster. The question is not, "How did it get made," because if you throw money at anyone and tell them to make a film, they will do so.
No. The question is "Why, oh why, did Steve Martin allow it to be made?" I think he needed the money to fight a nuisance lawsuit and was determined it not cost him anything. He knew the sequel was going to be so frightful, that out of pride, he wouldn't even count it's royalties as income.
The only way this sequel could not be an embarrassment is to have had Carl Gottlieb and Steve Martin revive the nation's favorite poor black family.
And "dcreasy2001" (aka Mark Blankfield?): It's just transparently obvious that you worked on this film in some sad capacity, and the only way you can feel better about your involvement is to be the sequel's lone cheerleader as an IMDb user comment. I was praying for you to veer over into satire, but alas, you were really making an effort at spin. Why not 10 stars?
+neg The Hazing is confused mumbo-jumbo that wants so hard to be The Evil Dead that it even references Bruce Campbell several times. The problem is, it is simply not in the same league as that terrific movie. This movie is nowhere near as original. The plot has been used before, by Kevin Tenney in Night of the Demons, and that was a lot more fun. This flick wastes too much time with complicated exposition before getting the kids into the spooky mansion and starting the demonic happenings.
Brad Dourif is, as usual, not given much to do here, but when he is on screen he puts in another over-the-top performance that would make Christopher Walken jealous. As for the acting of the kids, it's passable but by no means good. The shaky camera work is more annoying than clever or atmospheric. There are a few good moments when the first guy gets possessed and throws around some deadly one liners while dispatching his victims, but it was never scary for a second. The gore level is mid-range to low, but the director tries to make up for it by showing the actresses topless a few times. All in all, just okay if you have 87 minutes to waste.
+neg I have seen bad movies before, but this one takes the "Worst Movie of a Lifetime" award by far !! Anthony Hopkins has to be completely mentally ill to have his name attached to this one - anywhere ! I will never see another movie with him in it, directing it, etc., etc. ! I can't believe the other actors & actresses that I liked, (in this picture), that stooped so low to be a part of this disaster ! There must be some great drugs out there ! For anyone to not be embarrassed to be a part of such a film, is beyond me ! Save your money on this one ! HUGE FLOP from beginning to end ! Shame on you Mr. Hopkins ! Also, shame on Christian Slater ! I can't believe you put your reputations on the line for this one !
+neg You may want to know up front that I am not a Mormon, unlike a good number of those who have already reviewed this film. I mention this so you'll understand that the way I look at the film may differ greatly from those in the faith. For some, being critical of the film might be seen as being critical of the faith--and that is NOT my intention. So, my review is that of an outsider trying to look inside and learn more about who this man and his people were. Well, after seeing the film, I doubt if I have learned much at all. Since I have been a history teacher, I have a good basic understanding about Young as well as Joseph Smith as well as the teachings of the church. But anyone wanting to see this film to really learn anything will probably be disappointed because the film seems so gosh-darn nice--too nice and too unrealistic in its portrayal. Plus, you learn practically nothing about the church's beliefs other than they are nice people, work hard and some have many wives (and this latter part is only barely hinted at in the film). Instead, the people are almost cartoon-like in their simplistic portrayals. Joseph Smith and Brigham Young and their followers are angelic, the non-Mormons were all devils and Brian Donlevy (playing EXACTLY the same sort of role Edward G. Robinson later played in THE TEN COMMANDMENTS) is the trouble-maker who claims to be a Mormon but just comes along so the film can have a bad guy. It's all so very simple....too simple. Almost like an indoctrination film or infomercial.
Brigham Young especially was a very complex man--with many good points (an excellent organizer and visionary) as well as bad (don't even get me started on his views about Blacks within the church or intermarriage). To portray him in such vague terms is just plain silly. It's also a lot like how Gandhi was portrayed in the film with Ben Kingsley--only the facts that led to his being almost super-human were emphasized. Heck, now that I think about that, this is the trouble with most religious films--they often come off as one-dimensional, trite and bland. Let's have a full and more complete film of these men--one that will stick to facts and not emotional appeals.
Now if you can ignore the fact that you won't learn very much about the faith or its second leader, the film is enjoyable enough. It's obvious someone at 20th Century-Fox really cared about the film, as they had a wonderful cast of both premier actors (Tyrone Power), up and coming actors (Linda Darnell, Jane Darwell and Vincent Price) and wonderful character actors (Dean Jagger, John Carradine and Brian Donlevy). The film also had wonderful location shooting and lots of gloss. It just didn't have a lot to tell us other than they were all "swell". Plus, there were plenty of factual errors and a few just plain dumb scenes. A few of the mistakes include Young taking over the helm immediately after the death of Joseph Smith (it was three years later), no mention of the various Mormon denominations and splinter groups, talk of "gold in California"--even though it was 1847 and gold wouldn't be discovered until 1948, as well as no specific mention of polygamy or Smith's many wives. Just plain dumb scenes include Carradine pulling out a gun and waving it about in the courtroom scene--and no one seemed to care--even though it was a very hostile audience! Don't you think at least the judge would tell him to put it away and stop threatening people with it?!
One final comment. Do not, I repeat, do not watch this film when it's shown on American Movie Classics (a one great station that has sunk a lot in recent years). While I am critical of the film because of its simplistic message, I was horrified with the complete disrespect the station had for the church and its traditions. What I mean is this. The film was punctuated with ads for penis enlargement formulas as well as tons of pop-ups (some advertising a show that features the "sexiest cast"). Talk about disrespectful and gross and I would be just as offended if they did this for any other religious film. By doing this, they not only insult the faith but marginalize their market--after all, who is into hearing about these things AND the life of Brigham Young?! Is this a movie, in this form, that you can show to your kids or recommend to others?!
+pos Fifteen years later and Paris Is Burning is still aflame. This is a classic in black gay films, right up there with the other honorary black gay films, The Color Purple and Mahoganoy. This seminal work captures underground and underclass (i.e."underserved) black and Latin gay culture and community like no other work before or since, including all the sentimental Harlem Rennaissance gay retrospectives and renderings. They're good, but this is the best (dare I say the only "real") film you'll find on the subject. It's Relentlessy Cunty (the classic house music invention)comes to Hollywood, non-stop, hilarious camp (like only we do it) and dead-on social critique. All this by a white female director (who obviously must have been a Sister Gurl or Mizz Thing in a former life.) I could go on, but I think you get the point by now: I love this movie!
+pos I have been an admirer of Edward Burtynsky's work for years, and it was such a pleasure to be able to see the man at work, thanks to Jennifer Baichwal's documentary. The severe beauty of the ship-breaking yard in Bangladesh, the stone quarry in Vermont, the enormous assembly plant in China, the beleaguered old neighbourhoods in Shanghai that are just waiting to be torn down: these landscapes are captured so well by the photographer and the filmmaker.
At times I thought of old TV documentaries on abandoned coal mines and plastic-mold factories; the sort of stuff I grew up watching. Burtynsky's work has the great value of pointing out how the industrial activity has only shifted to Asia, it has not stopped. The strangest scene for me was the computer scrap-yard somewhere in China--the waste had a threatening air about it, while the workers were very jovial.
diff --git a/test/data_for_tests/io/imdb/test.txt b/test/data_for_tests/io/imdb/test.txt
index c9bfae74..68768ec6 100644
--- a/test/data_for_tests/io/imdb/test.txt
+++ b/test/data_for_tests/io/imdb/test.txt
@@ -1,2 +1,6 @@
neg Alan Rickman & Emma Thompson give good performances with southern/New Orleans accents in this detective flick. It's worth seeing for their scenes- and Rickman's scene with Hal Holbrook. These three actors mannage to entertain us no matter what the movie, it seems. The plot for the movie shows potential, but one gets the impression in watching the film that it was not pulled off as well as it could have been. The fact that it is cluttered by a rather uninteresting subplot and mostly uninteresting kidnappers really muddles things. The movie is worth a view- if for nothing more than entertaining performances by Rickman, Thompson, and Holbrook.
neg I have seen this movie and I did not care for this movie anyhow. I would not think about going to Paris because I do not like this country and its national capital. I do not like to learn french anyhow because I do not understand their language. Why would I go to France when I rather go to Germany or the United Kingdom? Germany and the United Kingdom are the nations I tolerate. Apparently the Olsen Twins do not understand the French language just like me. Therefore I will not bother the France trip no matter what. I might as well stick to the United Kingdom and meet single women and play video games if there is a video arcade. That is all.
+neg In Los Angeles, the alcoholic and lazy Hank Chinaski (Matt Dillon) performs a wide range of non-qualified functions just to get enough money to drink and gamble in horse races. His primary and only objective is writing and having sexy with dirty women.
"Factotum" is an uninteresting, pointless and extremely boring movie about an irresponsible drunken vagrant that works a couple of days or weeks just to get enough money to buy spirits and gamble, being immediately fired due to his reckless behavior. In accordance with IMDb, this character would be the fictional alter-ego of the author Charles Bukowski, and based on this story, I will certainly never read any of his novels. Honestly, if the viewer likes this theme of alcoholic couples, better off watching the touching and heartbreaking Hector Babenco's "Ironweed" or Marco Ferreri's "Storie di Ordinaria Follia" that is based on the life of the same writer. My vote is four.
Title (Brazil): "Factotum Sem Destino" ("Factotum Without Destiny")
+neg This film is bundled along with "Gli fumavano le Colt... lo chiamavano Camposanto" and both films leave a lot to be desired in the way of their DVD prints. First, both films are very dark--occasionally making it hard to see exactly what's happening. Second, neither film has subtitles and you are forced to watch a dubbed film--though "Il Prezzo del Potere" does seem to have a better dub. Personally, I always prefer subtitles but for the non-purists out there this isn't a problem. These DVD problems, however, are not the fault of the original film makers--just the indifferent package being marketed four decades later.
As for the film, it's about the assassination of President Garfield. This is a MAJOR problem, as Van Johnson looks about as much like Garfield as Judy Garland. In no way whatsoever does he look like Garfield. He's missing the beard, has the wrong hair color and style and is just not even close in any way (trust me on this, I am an American History teacher and we are paid to know these sort of things!). The real life Garfield was a Civil War general and looked like the guys on the Smith Brothers cough drop boxes. Plus, using some other actor to provide the voice for Johnson in the dubbing is just surreal. Never before or since has Van Johnson sounded quite so macho!! He was a fine actor...but certainly not a convincing general or macho president.
In addition to the stupid casting, President Garfield's death was in no way like this film. It's obvious that the film makers are actually cashing in on the crazy speculation about conspiracies concerning the death of JFK, not Garfield. Garfield was shot in Washington, DC (not Dallas) by a lone gunman with severe mental problems--not a group of men with rifles. However, according to most experts, what actually killed Garfield (over two months later) were incompetent doctors--who probed and probed and probed to retrieve a bullet (to no avail) and never bothered cleaning their hands or implements in the process. In other words, like George Washington (who was basically killed by repeated bloodletting when suffering with pneumonia) he died due to malpractice. In the movie they got nothing right whatsoever...other than indeed President Garfield was shot.
Because the film bears almost no similarity to real history, it's like a history lesson as taught from someone from another planet or someone with a severe brain injury. Why not also include ninjas, fighting robots and the Greek gods while you're at it?!?! Aside from some decent acting and production values, because the script is utter cow crap, I don't recommend anyone watch it. It's just a complete and utter mess.
+neg I only comment on really very good films and on utter rubbish. My aim is to help people who want to see great films to spend their time - and money - wisely.
I also want to stop people wasting their time on garbage, and want to publicize the fact that the director/producer of these garbage films can't get away with it for very long. We will find out who you are and will vote with out feet - and wallets.
This film clearly falls into the garbage category.
The director and writer is John Shiban. It's always a bad sign when the writer is also the director. Maybe he wants two pay cheques. He shouldn't get any. So remember the name - John SHIBAN. And if you see anything else by him, forget it.
I won't say anything about the plot - others have already. I am a little worried by how much the director likes to zoom in to the poor girl's face when she is crying and screaming. These long duration shots are a little worrying and may say something about the state of mind of Mr. Shiban. Maybe he should get psychiatric help.
Enough already. It's crap - don't waste your time on it.
+neg When you look at the cover and read stuff about it an entirely different type of movie comes to mind than what you get here. Then again maybe I read the summary for the other movie called "Mausolem" instead as there were two movies of this title released about the same time with both featuring plots that had key elements in common. However, reading stuff about that movie here I know I saw this one and not that one and that movie is even less what one would imagine a movie with that title would be about. I will be honest, I expect more of a zombie type picture and you get that in this movie to some degree. However, there is more stuff involving the occult and strange powers as the opening scene of the people being taken away by the coroner at the beginning of the film will attest to. The movie also has the old theme of kids going somewhere they do not belong to have some crazy party, in this case it is in fact a mausoleum. The other movie I do not think really has that key feature playing that prominent role in the movie and I see the score for this one is higher too, still it was just not the movie I was expecting.
diff --git a/test/data_for_tests/io/imdb/train.txt b/test/data_for_tests/io/imdb/train.txt
index d6ac6b68..bbf4d799 100644
--- a/test/data_for_tests/io/imdb/train.txt
+++ b/test/data_for_tests/io/imdb/train.txt
@@ -1,2 +1,6 @@
+neg The monster from Enemy Mine somehow made his way into a small mountain community, where he has taken up residence. He's being hunted by a female doctor-turned-vigilante who is out to exterminate him. This female assassin, who looks like a refugee from a Motley Crue video, rides around on a motorcycle and tries to save a bunch of kids who have chosen to have a Big Chill weekend right smack dab in the middle of the monster's turf. Decapitations and lots of blood are primarily in place to draw attention away from the story which limps along like a bad version of the Island of Dr. Moreau (and yes, it's worse than the one with Val Kilmer).
neg I'll try to use words to describe this on....
I saw the original, which was good in its own way, but back then I should have feared a sequel.
And I was 'afraid' when I picked this one up, but now that I've seen it, I have to say, it's even worse then I thought. Why these movies still get money still makes my mind spin.
Let's start with the actors;they aren't all that good, but it has to be said, some make heads turn by being just plain awful. But what can an actor do with a script like this one. It's trying to be a copy of the original only this time the places have changed, any form of story is gone and any attempt of actually coming up with something that hasn't been done before, fails miserably. In a futile attempt to get it up-to-date, they try to make it exciting by making use of the whole 'big-brother' theme , but that has been worn out ages ago and offers nothing but a filler for between the beginning and the end. An attempt was made to try to save the movie by making a ton of references to the '83 original, but it just ended up being plain funny and sometimes a bit sad. In conclusion, if you have nothing , and I mean nothing , to do... go watch it, or play Frisbee... with the DVD.... by yourself. It'll offer you the same amount of fun.. I promise
-pos This movie is totally wicked! It's really great to see MJH in a different role than her Sabrina character! The plot is totally cool, and the characters are excellently written. Definitely one of the best movies!!
+pos Most yeti pictures are fatally undermined by a grave paucity of energy and enthusiasm. Not so this gloriously bent, batty and berserk over-the-top Italian-made shot-in-Canada kitsch gut-buster: It's a wildly ripe and vigorously moronic ghastly marvel which reaches a stunning apotheosis of righteously over-baked "what the hell's going on?" crackpot excess and inanity.
A freighter ship crew discovers the body of a 30-foot yeti that resembles a hirsute 70's disco stud (complete with jumbo wavy afro) perfectly preserved in a large chunk of ice. They dethaw the beast, jolt him back to life with electric charges, grossly mistreat him, and keep the poor hairy Goliath in an enormous glass booth. Before you can say "Hey, the filmmakers are obviously ripping off 'King Kong'," our titanic abominable snowdude breaks free of his cage, grabs the first luscious nubile blonde Euro vixen (the gorgeous Pheonix Grant) he lays lustful eyes on, and storms away with his new lady love. The yeti gets recaptured and flown to Toronto to be showed off to a gawking audience. Of course, he breaks free again, nabs the vixen, and goes on the expected stomping around the city rampage.
The sublimely stupid dialogue (sample line: "Philosophy has no place in science, professor"), cheesy (far from) special effects (the horrendous transparent blue screen work and cruddy Tonka toy miniatures are especially uproarious in their very jaw-dropping awfulness), clunky (mis)direction, and a heavy-handed script that even attempts a clumsily sincere "Is the yeti a man or a beast?" ethical debate all combine together to create one of the single most delightfully ridiculous giant monster flicks to ever roar its absurd way across the big screen. Better still, we also have a few funky offbeat touches to add extra shoddy spice to the already succulently schlocky cinematic brew: the vixen accidentally brushes against one of the yeti's nipples, which causes it to harden and elicits a big, leering grin of approval from the lecherous behemoth (!); the vixen nurses the yeti's wounded hand while he makes goo-goo eyes at her, the yeti smashes windows with his feet while climbing a towering office building, and the furry fellow even breaks a man's neck with his toes (!!). Overall, this singularly screwball and shamefully unheralded should-be camp classic stands tall as a remarkable monolith of infectiously asinine celluloid lunacy that's eminently worthy of a substantial hardcore underground cult following.
+pos One of the best movies I ever saw was an Irish movie titled Philadelphia,Here I Come. I read the play before I saw the movie and loved them both. It's the story of a young man preparing to leave Ireland to go to America because he can't earn a living in Ireland. It is told both from the perspective of the young man(whom the other characters in the film can see) and another young man representing his uncensored thoughts and feelings., but who cannot be seen by the other characters in the film. It is a very sad movie, but deeply touching, and I would recommend this film to anyone who wants something to think about. I love any Irish movie, or almost any movie about Ireland, and any film that has the late Irish actor Donal McCann in it gets my vote.I would watch that man chew gum for 2 hours on screen, and unfortunately,I have.Terrible shame to have lost him so young.
+pos There is such rubbish on the cable movie channels that I hit a gem with this one. From beginning to end it had me gripped and deserves top marks.
Father of two sons hears messages from "God" to kill people who he is told are 'demons'.
When the opening credits showed the director as one of the cast that can often be a warning of a bad film; exceptionally it is the reverse here as the drama is non-stop from beginning to end.
And there is not one moment in the movie when one is not fully enthralled as there are no unnecessary or needless sub-plots, and the script is first class.
All the actors give wholly convincing performances especially the lead child actor who is exceptional.
This film is at least as good as the likes of 'Silence of the Lambs'.
+pos This is a nice piece of work. Very sexy and engaging enough plot to keep my interest throughout. Its main disadvantage is that it seems like it was made-for-TV: Full screen, and though there were several sex scenes, there was absolutely no nudity (but boy did it come close!). Strange, too, since Netflix shows that it was rated R.
Nonetheless, very titillating, and I wish Alicia Silverstone made more movies like this.
One Netflix reviewer stated that it was part of a series, but I have been unable to find out what series that is. I'd like to find out, though, because this movie was THAT good.
Walt D in LV. 8/23/2005
diff --git a/test/data_for_tests/io/yelp_review_full/dev.csv b/test/data_for_tests/io/yelp_review_full/dev.csv
new file mode 100755
index 00000000..ecc93b0b
--- /dev/null
+++ b/test/data_for_tests/io/yelp_review_full/dev.csv
@@ -0,0 +1,6 @@
+"2","Two meals, on the recommendation of a friend who lives near the place, and after the second trip, I was compelled to write. 'Rocky' would definitely describe the experiences.\n\nOn the first trip, I went to try their (at that time)raved about Reuben. And YET to find a true good Reuben in da burgh, I tried it.\n\nWell, they were out of the proper bread, and the guy had to run to the store to buy the closest thing he could find, which was not the proper bread, and instead of one of their 'raved about' Reubens, I received two mini-Reubens, which basically took the guts from one Reuben, and spread it out onto two sandwiches on regular sized bread. I ate it. It wasn't great, but they swore it was because they'd run out of the bread. Bread or not, it still wasn't great. The atmosphere was pleasant in that 'blue collar bar' kind of way, and the staff was very nice, but not a winning pitch on the Reuben.\n\nThe second trip was after a long day of moving furniture with the same friend. Sat in the back room, instead of the bar, which felt more like a restaurant, of course, with the big screen TV covering the sports of the moment.\n\nI was in the mood for dinner this time, and after a scan, decided on fried chicken and mashed potatoes with the salad bar. My friend ordered one of her faves, the breaded pork chops.\n\nWe hit the salad bar, which was uber-basic. Three soups (mostly vegetable loaded, which left me out), basic iceberg lettuce mix (very probably out of a bag), a few veggie toppings, and three or four dressings. It was a basic salad, no big deal. More or less an appetizer filler before the meal.\n\nThe mind-blower in this trip was the ordering of the fried chicken dinner. Our waiter looked like a 19 year old gas station attendant, skinny little blonde guy with a sweet but incredibly naive face, and an air of vapidity, which was confirmed when I placed my order. I asked what chicken pieces came in the dinner, and asked if it was possible to only get dark meat. I never imagined how confusing a question that could possibly be. It literally took him two trips back to the kitchen to 'ask', and the child honestly had no clue what 'white meat' and 'dark meat' meant. The first answer he came back with was that the chicken came in a pre-portioned prepared bag, kind of Kentucky Fried Chicken style...which didn't answer my question, thus prompting the second trip. \n\nAfter the second trip back I heard the cook holler 'Tell him I'll fix him up'. \n\nWell, the chicken was prepackaged dreck like you'd find in the freezer case of Walmart, tiny and not good, and the potatoes had that slight tinge of chem-spuds flavor, laden with some kind of chopped up green (parsley?), and a side of that basic brown gravy served up in 5 gallon buckets.\n\nThank goodness for the basic salad bar.\n\nEven my friend admitted that her pork chops were different and not what she'd expected. They also appeared to be from a freezer bag.\n\nThe irony was that the boy who didn't know white meat from dark meat, was chatting with some other customers...about baseball...and he was a genius about the mindless sport of baseball. Ahhhh da burgh.\n\nThird base? Nah...why bother when there are so many other options around. Go on in a grab a beer and chat black and gold if you happen to be in Carnegie...they can help you out all types of ways in that area. Just don't go hungry if you actually have tastebuds.\n\nFrom what I understand it 'used to be' really good homecooked food. But apparently, mama has left the kitchen."
+"4","I belong to this gym... I live in the South section of Pittsburgh, and I find that this gym is not too far from me. The staff is friendly, the equipment is quite good. You get two free personal training sessions when you join. They have lots of weights (which my boyfriend uses) and a decent cardio room. The only thing I would say is to increase some of the cardio equipment. Water is only $1 a bottle!"
+"3","I've been to Papa J's twice and had mixed experiences.\n\nBoth times I had the banana pepper appetizer, which is great and goes really well with the FRESH and delicious bread and cheese they give you at the start of your meal.\n\nFor entrees, me and my girlfriend have had mixed experience. I've had the fish sandwich (very good) and the eggplant parm sandwich (okay). My girlfriend got the salad with bread and basil on it, but the basil was over powering and the bread was soggy with the dressing. \n\nThe service is also a mixed bag. The first time our server went out of her way to take care of us and even MADE me cocktail sauce for my fish sandwich. The second time, the server was lackluster, didn't know anything about the menu and wasn't able to take proper care of us. \n\nI would return to Papa J's, but I my terrible experience last time isn't enough to say it would be my first pick of places to eat around Carnegie/Robinson."
+"4","Yay, I'm a fan but sometimes service is a little slow, it was very good for us this visit. Go to Papa j's every once in a while but mostly for the White Pizza. It is the best white pizza I have ever had. Order the white pizza on our visit this weekend... it has garlic, spinach, feta cheese and we usually add some veggie on top. It was delicious! Order fried calamari and it was OK...note to self next time try the calamari roman style.\n\nLike the dinning room with the hardwood floors and bright lighting. \n\nThe bar was jumping thou never go to the bar."
+"3","Had dinner at Papa J's with a group of 6. I loved how the restaurant is in a old brick building with large windows. It felt like a neighborhood restaurant. On a Saturday night, the restaurant was full but not crowded. We were seated in a room with poor acoustics. It was difficult to hear people at our table and the waitress. While she tried, I can see the asperation in her face when she had to repeat the specials to both sides of the table.\n\nPeople ordered bourbon on the rocks before dinner which seemed watered down, while my lemon drop was made nice. The bread was delicious! Can you describe it to be creamy? The fried zucchini was lightly breaded and not too oily. It was a large portion made up of 2 sliced zucchinis.\n\nWe ordered a variety of dishes. The pasta dish was dry with more pasta than sauce or meat. Those who ordered the fish special thought it was delicious. The shrimp dish was enjoyed as well. I had the chicken marsala which was pretty good. The marsala sauce wasn't too thick, and the chicken moist.\n\nHard to tell if the deserts were \""homemade.\"" The tiramisu and spumoni were small in portion and meant for one. \n\nOn the whole, I was on the fence with my overall impression of Papa J's. \""A-ok\"" probably is the best way to describe it."
+"2","Rather typical SnS. Had a good lunch crowd. Milkshake was good but not as good as EnP down the street. It took to long to get the burger for some reason, 25 minutes, I realized cooked to order but this is a little long for SnS. Ordered the Guacamole Steakburger and it only had a small portion of Gauc...not your usual amount..kitchen was not up to speed on portion sizing for some reason. Definitely did not look like the picture on the website. Oh well!"
diff --git a/test/data_for_tests/io/yelp_review_full/test.csv b/test/data_for_tests/io/yelp_review_full/test.csv
new file mode 100755
index 00000000..63d84891
--- /dev/null
+++ b/test/data_for_tests/io/yelp_review_full/test.csv
@@ -0,0 +1,6 @@
+"1","I got 'new' tires from them and within two weeks got a flat. I took my car to a local mechanic to see if i could get the hole patched, but they said the reason I had a flat was because the previous patch had blown - WAIT, WHAT? I just got the tire and never needed to have it patched? This was supposed to be a new tire. \nI took the tire over to Flynn's and they told me that someone punctured my tire, then tried to patch it. So there are resentful tire slashers? I find that very unlikely. After arguing with the guy and telling him that his logic was far fetched he said he'd give me a new tire \""this time\"". \nI will never go back to Flynn's b/c of the way this guy treated me and the simple fact that they gave me a used tire!"
+"1","Don't waste your time. We had two different people come to our house to give us estimates for a deck (one of them the OWNER). Both times, we never heard from them. Not a call, not the estimate, nothing."
+"1","All I can say is the worst! We were the only 2 people in the place for lunch, the place was freezing and loaded with kids toys! 2 bicycles, a scooter, and an electronic keyboard graced the dining room. A fish tank with filthy, slimy fingerprints smeared all over it is there for your enjoyment.\n\nOur food came... no water to drink, no tea, medium temperature food. Of course its cold, just like the room, I never took my jacket off! The plates are too small, you food spills over onto some semi-clean tables as you sit in your completely worn out booth seat. The fried noodles were out of a box and nasty, the shrimp was mushy, the fried rice was bright yellow.\n\nWe asked for water, they brought us 1 in a SOLO cup for 2 people. I asked for hot tea, they said 10 minutes. What Chinese restaurant does not have hot tea available upon request?\n\nOver all.... my first and last visit to this place. The only good point was that it was cheap, and deservingly so."
+"1","I have been to this restaurant twice and was disappointed both times. I won't go back. The first time we were there almost 3 hours. It took forever to order and then forever for our food to come and the place was empty. When I complained the manager was very rude and tried to blame us for taking to long to order. It made no sense, how could we order when the waitress wasn't coming to the table? After arguing with me he ended up taking $6 off of our $200+ bill. Ridiculous. If it were up to me I would have never returned. Unfortunately my family decided to go here again tonight. Again it took a long time to get our food. My food was cold and bland, my kids food was cold. My husbands salmon was burnt to a crisp and my sister in law took one bite of her trout and refused to eat any more because she claims it was so disgusting. The wedding soup and bread were good, but that's it! My drink sat empty throughout my meal and never got refilled even when I asked. Bad food, slow service and rude managers. I'll pass on this place if my family decides to go again. Not worth it at all with all the other good Italian options around."
+"1","Food was NOT GOOD at all! My husband & I ate here a couple weeks ago for the first time. I ordered a salad & basil pesto cream pasta & my husband ordered the spinach & feta pasta. The salad was just a huge plate of spring mix (nothing else in it) with WAY to much vinegar dressing. My lettuce was drowning in the vinegar. My pesto pasta had no flavor (did not taste like a cream sauce to me) & the pesto was so runny/watery & way too much sauce not enough noodles. My husband's pasta had even less flavor than mine. We ate about a quarter of the food & couldn't even finish it. We took it home & it was so bad I didn't even eat my leftovers. And I hate wasting food!! Plus the prices are expensive for the amount of food you get & of course the poor quality. Don't waste your time eating here. There are much better Italian restaurants in Pittsburgh."
+"3","This is a tiny Starbucks and it locations like this (although cute) makes you wonder if your really meant to hang out or just grab your coffee and leave. Leaving is always a good idea at this location anyway since you have a nice fountain in the back with benches and it is a central part of the Waterfront Shopping. \n\nStarbuck isn't my favorite coffee chain by any means. Is it just me or do all Starbuck coffees taste a little burnt and bitter? No matter how trendy, cool and upscale their establishments are I can't get around the yicky tasting bitterness of Staryucks regular coffees. Talk about over roasting a bean...Maybe something has changed with their regular coffee but I have not drank it in about a year. I am not one for soy caramel latte foofy stuff. Still I'll give the establishment tres estrellas for the fact that their espresso is acceptable and doesn't taste half as bad as the regular coffee bean."
diff --git a/test/data_for_tests/io/yelp_review_full/train.csv b/test/data_for_tests/io/yelp_review_full/train.csv
new file mode 100755
index 00000000..032d423a
--- /dev/null
+++ b/test/data_for_tests/io/yelp_review_full/train.csv
@@ -0,0 +1,6 @@
+"5","dr. goldberg offers everything i look for in a general practitioner. he's nice and easy to talk to without being patronizing; he's always on time in seeing his patients; he's affiliated with a top-notch hospital (nyu) which my parents have explained to me is very important in case something happens and you need surgery; and you can get referrals to see specialists without having to see him first. really, what more do you need? i'm sitting here trying to think of any complaints i have about him, but i'm really drawing a blank."
+"2","Unfortunately, the frustration of being Dr. Goldberg's patient is a repeat of the experience I've had with so many other doctors in NYC -- good doctor, terrible staff. It seems that his staff simply never answers the phone. It usually takes 2 hours of repeated calling to get an answer. Who has time for that or wants to deal with it? I have run into this problem with many other doctors and I just don't get it. You have office workers, you have patients with medical needs, why isn't anyone answering the phone? It's incomprehensible and not work the aggravation. It's with regret that I feel that I have to give Dr. Goldberg 2 stars."
+"4","Been going to Dr. Goldberg for over 10 years. I think I was one of his 1st patients when he started at MHMG. He's been great over the years and is really all about the big picture. It is because of him, not my now former gyn Dr. Markoff, that I found out I have fibroids. He explores all options with you and is very patient and understanding. He doesn't judge and asks all the right questions. Very thorough and wants to be kept in the loop on every aspect of your medical health and your life."
+"3","Got a letter in the mail last week that said Dr. Goldberg is moving to Arizona to take a new position there in June. He will be missed very much. \n\nI think finding a new doctor in NYC that you actually like might almost be as awful as trying to find a date!"
+"1","I don't know what Dr. Goldberg was like before moving to Arizona, but let me tell you, STAY AWAY from this doctor and this office. I was going to Dr. Johnson before he left and Goldberg took over when Johnson left. He is not a caring doctor. He is only interested in the co-pay and having you come in for medication refills every month. He will not give refills and could less about patients's financial situations. Trying to get your 90 days mail away pharmacy prescriptions through this guy is a joke. And to make matters even worse, his office staff is incompetent. 90% of the time when you call the office, they'll put you through to a voice mail, that NO ONE ever answers or returns your call. Both my adult children and husband have decided to leave this practice after experiencing such frustration. The entire office has an attitude like they are doing you a favor. Give me a break! Stay away from this doc and the practice. You deserve better and they will not be there when you really need them. I have never felt compelled to write a bad review about anyone until I met this pathetic excuse for a doctor who is all about the money."
+"5","Top notch doctor in a top notch practice. Can't say I am surprised when I was referred to him by another doctor who I think is wonderful and because he went to one of the best medical schools in the country. \nIt is really easy to get an appointment. There is minimal wait to be seen and his bedside manner is great."
diff --git a/test/data_for_tests/io/yelp_review_polarity/dev.csv b/test/data_for_tests/io/yelp_review_polarity/dev.csv
new file mode 100755
index 00000000..09228213
--- /dev/null
+++ b/test/data_for_tests/io/yelp_review_polarity/dev.csv
@@ -0,0 +1,6 @@
+"1","Hoofah."
+"1","Two meals, on the recommendation of a friend who lives near the place, and after the second trip, I was compelled to write. 'Rocky' would definitely describe the experiences.\n\nOn the first trip, I went to try their (at that time)raved about Reuben. And YET to find a true good Reuben in da burgh, I tried it.\n\nWell, they were out of the proper bread, and the guy had to run to the store to buy the closest thing he could find, which was not the proper bread, and instead of one of their 'raved about' Reubens, I received two mini-Reubens, which basically took the guts from one Reuben, and spread it out onto two sandwiches on regular sized bread. I ate it. It wasn't great, but they swore it was because they'd run out of the bread. Bread or not, it still wasn't great. The atmosphere was pleasant in that 'blue collar bar' kind of way, and the staff was very nice, but not a winning pitch on the Reuben.\n\nThe second trip was after a long day of moving furniture with the same friend. Sat in the back room, instead of the bar, which felt more like a restaurant, of course, with the big screen TV covering the sports of the moment.\n\nI was in the mood for dinner this time, and after a scan, decided on fried chicken and mashed potatoes with the salad bar. My friend ordered one of her faves, the breaded pork chops.\n\nWe hit the salad bar, which was uber-basic. Three soups (mostly vegetable loaded, which left me out), basic iceberg lettuce mix (very probably out of a bag), a few veggie toppings, and three or four dressings. It was a basic salad, no big deal. More or less an appetizer filler before the meal.\n\nThe mind-blower in this trip was the ordering of the fried chicken dinner. Our waiter looked like a 19 year old gas station attendant, skinny little blonde guy with a sweet but incredibly naive face, and an air of vapidity, which was confirmed when I placed my order. I asked what chicken pieces came in the dinner, and asked if it was possible to only get dark meat. I never imagined how confusing a question that could possibly be. It literally took him two trips back to the kitchen to 'ask', and the child honestly had no clue what 'white meat' and 'dark meat' meant. The first answer he came back with was that the chicken came in a pre-portioned prepared bag, kind of Kentucky Fried Chicken style...which didn't answer my question, thus prompting the second trip. \n\nAfter the second trip back I heard the cook holler 'Tell him I'll fix him up'. \n\nWell, the chicken was prepackaged dreck like you'd find in the freezer case of Walmart, tiny and not good, and the potatoes had that slight tinge of chem-spuds flavor, laden with some kind of chopped up green (parsley?), and a side of that basic brown gravy served up in 5 gallon buckets.\n\nThank goodness for the basic salad bar.\n\nEven my friend admitted that her pork chops were different and not what she'd expected. They also appeared to be from a freezer bag.\n\nThe irony was that the boy who didn't know white meat from dark meat, was chatting with some other customers...about baseball...and he was a genius about the mindless sport of baseball. Ahhhh da burgh.\n\nThird base? Nah...why bother when there are so many other options around. Go on in a grab a beer and chat black and gold if you happen to be in Carnegie...they can help you out all types of ways in that area. Just don't go hungry if you actually have tastebuds.\n\nFrom what I understand it 'used to be' really good homecooked food. But apparently, mama has left the kitchen."
+"2","I've lived in Pittsburgh for 6 years, and in Carnegie for over 2 years, and by far, this is the best greasy spoon joint I've found. If you can stomach the wait (no reservations, naturally), you'll enjoy overflowing plates of goodness, thanks to the well-seasoned griddle where all of the food is made. \n\nHere are the highlights:\n\n-Cheap: Breakfast for two can be well under $10, with lunch around the same.\n-Crowded: Get there early and expect to wait. They close pretty early on the weekends too (oddly, at 12:45pm)\n-Cash only\n-Huge portions: When ordering fries or homefries, always get the half order, unless you're a lumberjack\n-About those homefries: They're often undercooked. I've had better, believe me. My favorite things to eat in life are potato products.\n-My favorite item: hot sausage sandwich on thick Italian toast, with cheese, lettuce, tomato and mayo"
+"2","Classic breakfast joint. Grimy looking hole in the wall located on one end of a seedy looking strip mall. Window is opaque due to the grease so you can't hardly see inside. On the outside, there are about a dozen people waiting to get in. When you finally do get inside, you see that there are 15 tables and a counter, all occupied by people from all walks of life.\n\nWhat's the attraction behind this flea hole? The FOOD! Lots of it and dirt cheap. I sat at a vacant stool behind the formica counter and ordered the mixed grill. Potatoes, eggs, sausage, bacon and Italian toast. A giant mound of food guaranteed to sooth any hangover. I swear the full mixed grill had two pounds of food. Neat thing is that the grill is right in front of you so you can see your potatoes and eggs frying in a pool of fresh grease. All that food, plus coffee and tip for around ten bucks. Cash only, so put that plastic away.\n\nOnly bad thing that could happen is some douche bag from the Food Network or Travel Channel will make this place famous, and then I'll never be able to get in."
+"1","Some of the worst pizza I've ever had. We used a coupon from the paper for a 2 topping 8 cut Sicilian. First of all the pizza wasn't even cut through, and the sad attempt at cutting was so uneven that 4 of the slices were about an inch wide, while the others were about 4\"" each. The toppings were scarce, they used mini pepperoni and put maybe 8 on the whole pizza. The onions were huge chunks and the mushrooms were straight from a can. The worst part though was the thick doughy crust that tasted more like a fishy sourdough roll. I'm serious... It was so noticeable that it made me wonder if the dough was bad or if they for some weird reason put fish sauce in it. It was gross. \n\nWe also ordered steak and Italian hoagies. The veggies were old and wilted, and there was no dressing on either. The Italian had deli meat that was clearly bottom of the line and not very generous. The \""steak\"" (if you an call it that) was greyish instead of brown and looked like it was a processed meat chopped into pieces. No flavor or seasoning and the texture was reminiscent of spam. It was so bad that I only ate 1/4 of it and tossed the rest. \n\nI have ordered from here in the past and always been disappointed. I thought I would give them another try since I'd never ordered a Sicilian pizza from there. What a mistake. I will never order from them again!"
+"1","Terrible service. Food unremarkable. Waiter disappeared for 45 minutes to serve larger group due to staffing mismanagement. Saved his tip by discounting meal after I complained. All and all, a very crude and unpleasant dining experience for me and my guests. Not to be repeated, never again!"
diff --git a/test/data_for_tests/io/yelp_review_polarity/test.csv b/test/data_for_tests/io/yelp_review_polarity/test.csv
new file mode 100755
index 00000000..95ac34f3
--- /dev/null
+++ b/test/data_for_tests/io/yelp_review_polarity/test.csv
@@ -0,0 +1,6 @@
+"2","Contrary to other reviews, I have zero complaints about the service or the prices. I have been getting tire service here for the past 5 years now, and compared to my experience with places like Pep Boys, these guys are experienced and know what they're doing. \nAlso, this is one place that I do not feel like I am being taken advantage of, just because of my gender. Other auto mechanics have been notorious for capitalizing on my ignorance of cars, and have sucked my bank account dry. But here, my service and road coverage has all been well explained - and let up to me to decide. \nAnd they just renovated the waiting room. It looks a lot better than it did in previous years."
+"1","Last summer I had an appointment to get new tires and had to wait a super long time. I also went in this week for them to fix a minor problem with a tire they put on. They \""fixed\"" it for free, and the very next morning I had the same issue. I called to complain, and the \""manager\"" didn't even apologize!!! So frustrated. Never going back. They seem overpriced, too."
+"2","Friendly staff, same starbucks fair you get anywhere else. Sometimes the lines can get long."
+"1","The food is good. Unfortunately the service is very hit or miss. The main issue seems to be with the kitchen, the waiters and waitresses are often very apologetic for the long waits and it's pretty obvious that some of them avoid the tables after taking the initial order to avoid hearing complaints."
+"2","Even when we didn't have a car Filene's Basement was worth the bus trip to the Waterfront. I always find something (usually I find 3-4 things and spend about $60) and better still, I am always still wearing the clothes and shoes 3 months later. \n\nI kind of suspect this is the best shopping in Pittsburgh; it's much better than the usual department stores, better than Marshall's and TJ Maxx and better than the Saks downtown, even when it has a sale. Selection, bargains AND quality.\n\nI like this Filene's better than Gabriel Brothers, which are harder to get to. Gabriel Brothers are a real discount shopper's challenge and I'm afraid I didn't live in Pittsburgh long enough to develop the necessary skills . . . Filene's was still up and running in June 2007 when I left town."
+"2","Picture Billy Joel's \""Piano Man\"" DOUBLED mixed with beer, a rowdy crowd, and comedy - Welcome to Sing Sing! A unique musical experience found in Homestead.\n\nIf you're looking to grab a bite to eat or a beer, come on in! Serving food and brews from Rock Bottom Brewery, Sing Sing keeps your tummy full while you listen to two (or more) amazingly talented pianists take your musical requests. They'll play anything you'd like, for tips of course. Wanting to hear Britney Spears? Toto? Duran Duran? Yep, they play that... new or old.\n\nThe crowd makes the show, so make sure you come ready for a good time. If the crowd is dead, it's harder for the Guys to get a reaction. If you're wanting to have some fun, it can be a GREAT time! It's the perfect place for Birthday parties - especially if you want to embarrass a friend. The guys will bring them up to the pianos and perform a little ditty. For being a good sport, you get the coveted Sing Sing bumper sticker. Now who wouldn't want that?\n\nDueling Pianos and brews... time to Shut Up & Sing Sing!"
diff --git a/test/data_for_tests/io/yelp_review_polarity/train.csv b/test/data_for_tests/io/yelp_review_polarity/train.csv
new file mode 100755
index 00000000..6b72a7d6
--- /dev/null
+++ b/test/data_for_tests/io/yelp_review_polarity/train.csv
@@ -0,0 +1,6 @@
+"1","Unfortunately, the frustration of being Dr. Goldberg's patient is a repeat of the experience I've had with so many other doctors in NYC -- good doctor, terrible staff. It seems that his staff simply never answers the phone. It usually takes 2 hours of repeated calling to get an answer. Who has time for that or wants to deal with it? I have run into this problem with many other doctors and I just don't get it. You have office workers, you have patients with medical needs, why isn't anyone answering the phone? It's incomprehensible and not work the aggravation. It's with regret that I feel that I have to give Dr. Goldberg 2 stars."
+"2","Been going to Dr. Goldberg for over 10 years. I think I was one of his 1st patients when he started at MHMG. He's been great over the years and is really all about the big picture. It is because of him, not my now former gyn Dr. Markoff, that I found out I have fibroids. He explores all options with you and is very patient and understanding. He doesn't judge and asks all the right questions. Very thorough and wants to be kept in the loop on every aspect of your medical health and your life."
+"1","I don't know what Dr. Goldberg was like before moving to Arizona, but let me tell you, STAY AWAY from this doctor and this office. I was going to Dr. Johnson before he left and Goldberg took over when Johnson left. He is not a caring doctor. He is only interested in the co-pay and having you come in for medication refills every month. He will not give refills and could less about patients's financial situations. Trying to get your 90 days mail away pharmacy prescriptions through this guy is a joke. And to make matters even worse, his office staff is incompetent. 90% of the time when you call the office, they'll put you through to a voice mail, that NO ONE ever answers or returns your call. Both my adult children and husband have decided to leave this practice after experiencing such frustration. The entire office has an attitude like they are doing you a favor. Give me a break! Stay away from this doc and the practice. You deserve better and they will not be there when you really need them. I have never felt compelled to write a bad review about anyone until I met this pathetic excuse for a doctor who is all about the money."
+"1","I'm writing this review to give you a heads up before you see this Doctor. The office staff and administration are very unprofessional. I left a message with multiple people regarding my bill, and no one ever called me back. I had to hound them to get an answer about my bill. \n\nSecond, and most important, make sure your insurance is going to cover Dr. Goldberg's visits and blood work. He recommended to me that I get a physical, and he knew I was a student because I told him. I got the physical done. Later, I found out my health insurance doesn't pay for preventative visits. I received an $800.00 bill for the blood work. I can't pay for my bill because I'm a student and don't have any cash flow at this current time. I can't believe the Doctor wouldn't give me a heads up to make sure my insurance would cover work that wasn't necessary and was strictly preventative. The office can't do anything to help me cover the bill. In addition, the office staff said the onus is on me to make sure my insurance covers visits. Frustrating situation!"
+"2","All the food is great here. But the best thing they have is their wings. Their wings are simply fantastic!! The \""Wet Cajun\"" are by the best & most popular. I also like the seasoned salt wings. Wing Night is Monday & Wednesday night, $0.75 whole wings!\n\nThe dining area is nice. Very family friendly! The bar is very nice is well. This place is truly a Yinzer's dream!! \""Pittsburgh Dad\"" would love this place n'at!!"
+"1","Wing sauce is like water. Pretty much a lot of butter and some hot sauce (franks red hot maybe). The whole wings are good size and crispy, but for $1 a wing the sauce could be better. The hot and extra hot are about the same flavor/heat. The fish sandwich is good and is a large portion, sides are decent."
diff --git a/test/io/loader/test_classification_loader.py b/test/io/loader/test_classification_loader.py
index f099c1b2..fdfc9008 100644
--- a/test/io/loader/test_classification_loader.py
+++ b/test/io/loader/test_classification_loader.py
@@ -1,5 +1,7 @@
import unittest
+
+from fastNLP.io import DataBundle
from fastNLP.io.loader.classification import YelpFullLoader
from fastNLP.io.loader.classification import YelpPolarityLoader
from fastNLP.io.loader.classification import IMDBLoader
@@ -8,6 +10,7 @@ from fastNLP.io.loader.classification import SSTLoader
from fastNLP.io.loader.classification import ChnSentiCorpLoader
import os
+
@unittest.skipIf('TRAVIS' in os.environ, "Skip in travis")
class TestDownload(unittest.TestCase):
def test_download(self):
@@ -21,7 +24,26 @@ class TestDownload(unittest.TestCase):
class TestLoad(unittest.TestCase):
- def test_load(self):
- for loader in [IMDBLoader]:
- data_bundle = loader().load('test/data_for_tests/io/imdb')
- print(data_bundle)
+ def test_process_from_file(self):
+ data_set_dict = {
+ 'yelp.p': ('test/data_for_tests/io/yelp_review_polarity', YelpPolarityLoader, (6, 6, 6), False),
+ 'yelp.f': ('test/data_for_tests/io/yelp_review_full', YelpFullLoader, (6, 6, 6), False),
+ 'sst-2': ('test/data_for_tests/io/SST-2', SST2Loader, (5, 5, 5), True),
+ 'sst': ('test/data_for_tests/io/SST', SSTLoader, (6, 6, 6), False),
+ 'imdb': ('test/data_for_tests/io/imdb', IMDBLoader, (6, 6, 6), False),
+ }
+ for k, v in data_set_dict.items():
+ path, loader, data_set, warns = v
+ with self.subTest(loader=loader):
+ if warns:
+ with self.assertWarns(Warning):
+ data_bundle = loader().load(path)
+ else:
+ data_bundle = loader().load(path)
+
+ self.assertTrue(isinstance(data_bundle, DataBundle))
+ self.assertEqual(len(data_set), data_bundle.num_dataset)
+ for x, y in zip(data_set, data_bundle.iter_datasets()):
+ name, dataset = y
+ self.assertEqual(x, len(dataset))
+
diff --git a/test/io/loader/test_matching_loader.py b/test/io/loader/test_matching_loader.py
index cb1334e0..8d6e182c 100644
--- a/test/io/loader/test_matching_loader.py
+++ b/test/io/loader/test_matching_loader.py
@@ -1,5 +1,7 @@
import unittest
+
+from fastNLP.io import DataBundle
from fastNLP.io.loader.matching import RTELoader
from fastNLP.io.loader.matching import QNLILoader
from fastNLP.io.loader.matching import SNLILoader
@@ -23,7 +25,23 @@ class TestMatchingDownload(unittest.TestCase):
class TestMatchingLoad(unittest.TestCase):
def test_load(self):
- for loader in [RTELoader]:
- data_bundle = loader().load('test/data_for_tests/io/rte')
- print(data_bundle)
+ data_set_dict = {
+ 'RTE': ('test/data_for_tests/io/RTE', RTELoader, (5, 5, 5), True),
+ 'SNLI': ('test/data_for_tests/io/SNLI', SNLILoader, (5, 5, 5), False),
+ 'QNLI': ('test/data_for_tests/io/QNLI', QNLILoader, (5, 5, 5), True),
+ 'MNLI': ('test/data_for_tests/io/MNLI', MNLILoader, (5, 5, 5, 5, 6), True),
+ }
+ for k, v in data_set_dict.items():
+ path, loader, instance, warns = v
+ if warns:
+ with self.assertWarns(Warning):
+ data_bundle = loader().load(path)
+ else:
+ data_bundle = loader().load(path)
+
+ self.assertTrue(isinstance(data_bundle, DataBundle))
+ self.assertEqual(len(instance), data_bundle.num_dataset)
+ for x, y in zip(instance, data_bundle.iter_datasets()):
+ name, dataset = y
+ self.assertEqual(x, len(dataset))
diff --git a/test/io/pipe/test_classification.py b/test/io/pipe/test_classification.py
index 45c276a3..88bf6921 100644
--- a/test/io/pipe/test_classification.py
+++ b/test/io/pipe/test_classification.py
@@ -1,9 +1,11 @@
import unittest
import os
+from fastNLP.io import DataBundle
from fastNLP.io.pipe.classification import SSTPipe, SST2Pipe, IMDBPipe, YelpFullPipe, YelpPolarityPipe
from fastNLP.io.pipe.classification import ChnSentiCorpPipe
+
@unittest.skipIf('TRAVIS' in os.environ, "Skip in travis")
class TestClassificationPipe(unittest.TestCase):
def test_process_from_file(self):
@@ -27,4 +29,35 @@ class TestCNClassificationPipe(unittest.TestCase):
for pipe in [ChnSentiCorpPipe]:
with self.subTest(pipe=pipe):
data_bundle = pipe(bigrams=True, trigrams=True).process_from_file()
- print(data_bundle)
\ No newline at end of file
+ print(data_bundle)
+
+
+class TestRunClassificationPipe(unittest.TestCase):
+ def test_process_from_file(self):
+ data_set_dict = {
+ 'yelp.p': ('test/data_for_tests/io/yelp_review_polarity', YelpPolarityPipe, (6, 6, 6), (1176, 2), False),
+ 'yelp.f': ('test/data_for_tests/io/yelp_review_full', YelpFullPipe, (6, 6, 6), (1023, 5), False),
+ 'sst-2': ('test/data_for_tests/io/SST-2', SST2Pipe, (5, 5, 5), (139, 2), True),
+ 'sst': ('test/data_for_tests/io/SST', SSTPipe, (6, 354, 6), (232, 5), False),
+ 'imdb': ('test/data_for_tests/io/imdb', IMDBPipe, (6, 6, 6), (1670, 2), False),
+ }
+ for k, v in data_set_dict.items():
+ path, pipe, data_set, vocab, warns = v
+ with self.subTest(pipe=pipe):
+ if warns:
+ with self.assertWarns(Warning):
+ data_bundle = pipe(tokenizer='raw').process_from_file(path)
+ else:
+ data_bundle = pipe(tokenizer='raw').process_from_file(path)
+
+ self.assertTrue(isinstance(data_bundle, DataBundle))
+ self.assertEqual(len(data_set), data_bundle.num_dataset)
+ for x, y in zip(data_set, data_bundle.iter_datasets()):
+ name, dataset = y
+ self.assertEqual(x, len(dataset))
+
+ self.assertEqual(len(vocab), data_bundle.num_vocab)
+ for x, y in zip(vocab, data_bundle.iter_vocabs()):
+ name, vocabs = y
+ self.assertEqual(x, len(vocabs))
+
diff --git a/test/io/pipe/test_matching.py b/test/io/pipe/test_matching.py
index 932d8289..8b0076c2 100644
--- a/test/io/pipe/test_matching.py
+++ b/test/io/pipe/test_matching.py
@@ -2,6 +2,7 @@
import unittest
import os
+from fastNLP.io import DataBundle
from fastNLP.io.pipe.matching import SNLIPipe, RTEPipe, QNLIPipe, MNLIPipe
from fastNLP.io.pipe.matching import SNLIBertPipe, RTEBertPipe, QNLIBertPipe, MNLIBertPipe
@@ -29,6 +30,37 @@ class TestMatchingBertPipe(unittest.TestCase):
class TestRunMatchingPipe(unittest.TestCase):
def test_load(self):
- for pipe in [RTEPipe, RTEBertPipe]:
- data_bundle = pipe(tokenizer='raw').process_from_file('test/data_for_tests/io/rte')
- print(data_bundle)
+ data_set_dict = {
+ 'RTE': ('test/data_for_tests/io/RTE', RTEPipe, RTEBertPipe, (5, 5, 5), (449, 2), True),
+ 'SNLI': ('test/data_for_tests/io/SNLI', SNLIPipe, SNLIBertPipe, (5, 5, 5), (110, 3), False),
+ 'QNLI': ('test/data_for_tests/io/QNLI', QNLIPipe, QNLIBertPipe, (5, 5, 5), (372, 2), True),
+ 'MNLI': ('test/data_for_tests/io/MNLI', MNLIPipe, MNLIBertPipe, (5, 5, 5, 5, 6), (459, 3), True),
+ }
+ for k, v in data_set_dict.items():
+ path, pipe1, pipe2, data_set, vocab, warns = v
+ if warns:
+ with self.assertWarns(Warning):
+ data_bundle1 = pipe1(tokenizer='raw').process_from_file(path)
+ data_bundle2 = pipe2(tokenizer='raw').process_from_file(path)
+ else:
+ data_bundle1 = pipe1(tokenizer='raw').process_from_file(path)
+ data_bundle2 = pipe2(tokenizer='raw').process_from_file(path)
+
+ self.assertTrue(isinstance(data_bundle1, DataBundle))
+ self.assertEqual(len(data_set), data_bundle1.num_dataset)
+ for x, y in zip(data_set, data_bundle1.iter_datasets()):
+ name, dataset = y
+ self.assertEqual(x, len(dataset))
+ self.assertEqual(len(data_set), data_bundle2.num_dataset)
+ for x, y in zip(data_set, data_bundle2.iter_datasets()):
+ name, dataset = y
+ self.assertEqual(x, len(dataset))
+
+ self.assertEqual(len(vocab), data_bundle1.num_vocab)
+ for x, y in zip(vocab, data_bundle1.iter_vocabs()):
+ name, vocabs = y
+ self.assertEqual(x, len(vocabs))
+ self.assertEqual(len(vocab), data_bundle2.num_vocab)
+ for x, y in zip(vocab, data_bundle1.iter_vocabs()):
+ name, vocabs = y
+ self.assertEqual(x + 1 if name == 'words' else x, len(vocabs))