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.
1446 Commits
3 Branches
25 MB
0 Download
 
 
 
 
 
Tree: 1cc7f0b5e7
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '1cc7f0b5e7'
${ noResults }
fastNLP/reproduction/seqence_labelling/ner
yh 9529f89abd 增加DataBundle的方法；增加BilSTMCRF的注释 5 years ago
..
model 1.增加sequence labelling中bert ner; 2.将print替换为logger 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_bert.py 1.增加sequence labelling中bert ner; 2.将print替换为logger 5 years ago
train_cnn_lstm_crf_conll2003.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_idcnn.py 1.增加sequence labelling中bert ner; 2.将print替换为logger 5 years ago
train_ontonote.py 增加DataBundle的方法；增加BilSTMCRF的注释 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