Bert: The fine_tune codes for NER CoNLL2003 with bert_base(cased) model

Created on 10 Jan 2019  路  3Comments  路  Source: google-research/bert

Could you share your fine_tune codes for NER CoNLL2003 with bert_base(cased) model? I met some problems to redo the reported experiment result ( f1 - 92. 4) .

picture HAWLYQ
👍9

Most helpful comment

Yes, it would be great to have that code.

I have the same issue, that my code only achieves a performance of about F1: 90.0 (test set).

picture nreimers on 10 Jan 2019
👍6

All 3 comments

Yes, it would be great to have that code.

I have the same issue, that my code only achieves a performance of about F1: 90.0 (test set).

nreimers picture nreimers on 10 Jan 2019
👍6

I haven't tried on the test set but I've also only gotten around 93 F1 on the dev set while the advertised performance is higher than 96 F1. For a start, reporting the hyperparameters that this experiment was run with would be helpful.

davisyoshida picture davisyoshida on 17 Mar 2019

Hi, did you finally reproduce the results (with document context)?

wangxinyu0922 picture wangxinyu0922 on 27 Oct 2020
👍1
Was this page helpful?
0 / 5 - 0 ratings

Related issues

qiugen picture qiugen  路  4Comments
hmxv2 picture hmxv2  路  4Comments
waallf picture waallf  路  4Comments
sharavsambuu picture sharavsambuu  路  3Comments
okgrammer picture okgrammer  路  4Comments