Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
yh_cc 5e9c406761 | 5 years ago | |
---|---|---|
.. | ||
Biaffine_parser | 5 years ago | |
CNN-sentence_classification | 6 years ago | |
Char-aware_NLM | 6 years ago | |
Chinese_word_segmentation | 5 years ago | |
HAN-document_classification | 6 years ago | |
LSTM+self_attention_sentiment_analysis | 5 years ago | |
POS_tagging | 5 years ago | |
README.md | 5 years ago | |
__init__.py | 5 years ago |
这里复现了在fastNLP中实现的模型,旨在达到与论文中相符的性能。
复现的模型有:
任务 | 数据集 | SOTA | 模型表现 |
---|---|---|---|
Pos Tagging | CTB 9.0 | - | ACC 92.31 |
Pos Tagging | CONLL 2012 | - | ACC 96.51 |
Named Entity Recognition | CONLL 2012 | - | F1 85.66 |
Text Classification | SST | - | 49.18 |
Natural Language Inference | SNLI | - | 83.76 |
# for sequence labeling(ner, pos tagging, etc)
from fastNLP.models.star_transformer import STSeqLabel
model = STSeqLabel(
vocab_size=10000, num_cls=50,
emb_dim=300)
# for sequence classification
from fastNLP.models.star_transformer import STSeqCls
model = STSeqCls(
vocab_size=10000, num_cls=50,
emb_dim=300)
# for natural language inference
from fastNLP.models.star_transformer import STNLICls
model = STNLICls(
vocab_size=10000, num_cls=50,
emb_dim=300)
一款轻量级的自然语言处理(NLP)工具包,目标是减少用户项目中的工程型代码,例如数据处理循环、训练循环、多卡运行等
Python Jupyter Notebook Text CSV Markdown