the F1-Score of CoNLL 2003 English dataset

monikkinom / ner-lstm

Named Entity Recognition using multilayered bidirectional LSTM

540 stars 182 forks source link

the F1-Score of CoNLL 2003 English dataset #31

Open sssongss opened 6 years ago

sssongss commented 6 years ago

We execute the code on CoNLL 2003 English dataset using Word2Vec 311 dimensions, but we got the results of 83.68%(Test_a) and 79.68%(Test_b), about 10% lower than the report.

zhuiqiuzhuoyue commented 6 years ago

@sssongss How did you successfully run these source code? I have many problems at present and can't run successfully. I'm very anxious. I hope you can help me. My contact information: (email:2936067644@qq.com) (QQ: 2936067644) (WeChat: A15603398058). There will be abundant remuneration and money.

gopi1410 commented 5 years ago

@zhuiqiuzhuoyue I have detailed the steps and updated code to support TF 1.4 here
https://github.com/gopi1410/ner-lstm