mirror of
https://gitee.com/fastnlp/fastNLP.git
synced 2024-12-04 21:28:01 +08:00
.. | ||
data | ||
model | ||
test | ||
__init__.py | ||
README.md | ||
train_cnn_lstm_crf_conll2003.py | ||
train_idcnn.py | ||
train_ontonote.py |
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 |