hummingbird
/
fastNLP
Not watched
2
0
Fork 0
Code
Releases 13 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
1208 Commits
3 Branches
25 MB
0 Download
 
 
 
 
 
Tree: 0032f7788a
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '0032f7788a'
${ noResults }
fastNLP/reproduction
yh cf64412dad merge docs 5 years ago
..
Star_transformer 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 5 years ago
Summarization 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 5 years ago
coreference_resolution 将DataInfo修改为DataBundle 5 years ago
joint_cws_parse 1. 增强BertEmbedding使其可以自动判断token_type_ids; 2.增加CrossEntropyLoss中对label dimension的报错处理 5 years ago
legacy Merge branch 'dev0.5.0' of https://github.com/fastnlp/fastNLP into dev0.5.0 5 years ago
matching 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 5 years ago
seqence_labelling fix a serial bugs on importing 5 years ago
text_classification [verify] add data source in readme 5 years ago
README.md update README.md 5 years ago
__init__.py 1. 将pad的功能从FieldArray中剥离出来，使用Padder完成各种padding操作。 5 years ago
utils.py Merge pull request #177 from SrWYG/dev0.5.0 5 years ago

README.md

模型复现

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:

任务复现

Text Classification (文本分类)

Matching (自然语言推理/句子匹配)

Sequence Labeling (序列标注)

Coreference Resolution (共指消解)

Summarization (摘要)

...

Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

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