Juntao Yu

@zhaoxf4 I've checked your data, they are identical to mine and I also tested on my best model they give the same results I reported in the paper. The log...

@wangxinyu0922 I did 3 runs using BiLSMT+CRF model on CoNLL 02 English, the best I can get is 91.9 a bit lower than the BERT paper's 92.8. They might get...

Yes, it is the same as in my paper, apart from the window_size is not 128 but 512, so make sure you download the latest **extract_bert_features.sh** I train it on...

@wangxinyu0922 the use_lee_lstm will not affect the results:) the final version does use the custom LSTM from Lee et al 2018 system. It is just some experiment I did to...

I didn't set seed for the final version. I tried some times ago, and for an unknown reason, after I fixed both python seed and TensorFlow seed I still get...

所有的细节都已经在代码里了：）如果你完全用我给出的参数来跑试验的话，至少会有80+，在我跑的重复试验里没有低于过80的。 麻烦你把日志贴上来我帮你看一下。

你可以从这里下载 https://www.dropbox.com/s/ppqkcbz5sjpufwe/genia_acl2020_biaffine.zip?dl=0

没看懂你的问题能从新解释一下不：）

这个mask在flatten以后就刚好对应gold label的indices （0,0),(0,1)...(1,1)... 变成其他形状就不match gold label了啊

常用的数据集暂时没有这样的需求所以我也没有试过，估计是可以的你把loss改成sigmoid应该就可以的。我之前的[mention detecter](https://github.com/juntaoy/dali-md/blob/master/biaffine_md.py)的论文里面用的就是sigmoid函数（不过是binary的，num_labels = 1) 所以应该可行的。