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.
1117 Commits
3 Branches
25 MB
1 Download
 
 
 
 
 
Tree: 807a8f1fb3
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '807a8f1fb3'
${ noResults }
fastNLP/reproduction
yh 807a8f1fb3 1. BucketSampler不需要自己传入batch_size了，由Trainer自动设置 6 years ago
..
Star_transformer [bug fix] sst loader, star-transformer 6 years ago
Summarization add rouge in readme 6 years ago
coreference_resolution 将DataInfo修改为DataBundle 6 years ago
joint_cws_parse 将DataInfo修改为DataBundle 6 years ago
legacy 1. BucketSampler不需要自己传入batch_size了，由Trainer自动设置 6 years ago
matching fix bug in matching DataLoader 6 years ago
seqence_labelling 1. BucketSampler不需要自己传入batch_size了，由Trainer自动设置 6 years ago
text_classification 1. BucketSampler不需要自己传入batch_size了，由Trainer自动设置 6 years ago
README.md update README.md 6 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。 6 years ago
utils.py Merge pull request #177 from SrWYG/dev0.5.0 6 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