test/fastNLP
1
0
Fork 0
mirror of https://gitee.com/fastnlp/fastNLP.git synced 2024-12-05 05:38:31 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
a88fe24c34
fastNLP/reproduction/seqence_labelling/ner
History
yh 0a33a32081 Merge branch 'dev0.5.0' of https://github.com/fastnlp/fastNLP into dev0.5.0 
# Conflicts:
#	fastNLP/modules/encoder/embedding.py
#	reproduction/seqence_labelling/ner/train_ontonote.py
#	reproduction/text_classification/model/lstm.py
2019-07-12 09:56:35 +08:00
..
data fix import bug 2019-07-11 14:44:23 +08:00
model fix import bug 2019-07-11 14:44:23 +08:00
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. 2019-06-18 10:02:24 +08:00
__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. 2019-06-18 10:02:24 +08:00
README.md ner的readme更新 2019-07-02 11:32:45 +08:00
train_cnn_lstm_crf_conll2003.py 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 2019-07-12 04:07:47 +08:00
train_idcnn.py 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 2019-07-12 04:07:47 +08:00
train_ontonote.py Merge branch 'dev0.5.0' of https://github.com/fastnlp/fastNLP into dev0.5.0 2019-07-12 09:56:35 +08:00

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