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.
1001 Commits
3 Branches
25 MB
0 Download
 
 
 
 
 
Tree: 368733d98c
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '368733d98c'
${ noResults }
fastNLP/reproduction/seqence_labelling/ner
yunfan f1adb0f915 add ID-CNN 5 years ago
..
data 1. 在vocabulary的from_dataset中增加no_create_entry_dataset选项，用于传递dev和test 5 years ago
model add ID-CNN 5 years ago
test 新增NER的数据加载与模型代码; 修改metric中的typo; 修改LSTM中的默认初始化将forget gate设置为1. 5 years ago
README.md ner的readme更新 5 years ago
__init__.py 新增NER的数据加载与模型代码; 修改metric中的typo; 修改LSTM中的默认初始化将forget gate设置为1. 5 years ago
train_cnn_lstm_crf_conll2003.py 1.修改CrossEntropyLoss中存在的反直觉bug; 2.更新sequence labeling 5 years ago
train_ontonote.py 1.修改CrossEntropyLoss中存在的反直觉bug; 2.更新sequence labeling 5 years ago

README.md

NER任务模型复现

这里使用fastNLP复现经典的BiLSTM-CNN的NER任务的模型，旨在达到与论文中相符的性能。

论文链接Named Entity Recognition with Bidirectional LSTM-CNNs

数据集及复现结果汇总

使用fastNLP复现的结果vs论文汇报结果(/前为fastNLP实现，后面为论文报道)

model name Conll2003 Ontonotes
BiLSTM-CNN 91.17/90.91 86.47/86.35
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