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.
1281 Commits
3 Branches
25 MB
0 Download
 
 
 
 
 
Tree: ffd5fd8135
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'ffd5fd8135'
${ noResults }
fastNLP/reproduction/seqence_labelling/cws
yh_cc 584a92c64c 1.增加sequence labeling任务的数据说明; 2.增加对CWSPipe的引用 5 years ago
..
data 1.修复Embedding中潜在的寻找路径失败; 2.reproduction中增加分词模型; 3.修改ner模型为最新的pipe版本 5 years ago
model 1.修复Embedding中潜在的寻找路径失败; 2.reproduction中增加分词模型; 3.修改ner模型为最新的pipe版本 5 years ago
readme.md 1.增加sequence labeling任务的数据说明; 2.增加对CWSPipe的引用 5 years ago
train_bilstm_crf.py 1.修复Embedding中潜在的寻找路径失败; 2.reproduction中增加分词模型; 3.修改ner模型为最新的pipe版本 5 years ago
train_shift_relay.py 1.修复Embedding中潜在的寻找路径失败; 2.reproduction中增加分词模型; 3.修改ner模型为最新的pipe版本 5 years ago

readme.md

四个数据集的统计信息，最原始的数据可以从http://sighan.cs.uchicago.edu/bakeoff2005/下载。

pku # of sents # of tokens
train 17173 1650222
dev 1881 176226
test 1944 172733
total 20998 1999181
cityu # of sents # of tokens
train 47696 2164907
dev 5323 238447
test 1492 67690
total 54511 2471044
msra # of sents # of tokens
train 78242 3644550
dev 8676 405919
test 3985 184355
total 90903 4234824
as # of sents # of tokens
train 638273 7536586
dev 70680 831464
test 14429 197681
total 723382 8565731
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