YANG Zhiwei

Why the result is better than that in the papers? #87

1

Hi, I run the code on the conll2003 dataset, however, the result of the code is better than that reported in the paper. I am curious about where to get...

main.py : TypeError:__init__() got an unexpected keyword argument 'save_checkpoints_secs'

2

I got this error caused by the argument in the 'RunConfig' function when I run the 'python main.py' command. However, it still showed that 'Estimator' object has no attribute 'eval_dir'....

Why the CoNLL 2003 NER dataset isn't annotated by BIOES tags as the paper described?

2

Hi, Thank you for your excellent work. As you described in the paper, you have adopted BIOES tagging scheme in the experiment. However, it seems that the CoNLL 2003 NER...

As described in Fig2 of the paper, the label embedding is concated with the output of BiLSTM of Layer1 and Layer2, as well as the output of Label Attention Inference...

How to reproduce the result as Table 3 described in the paper?

1

Hi, I am trying to reproduce the result as described in Table 3 of the paper [https://arxiv.org/abs/1903.10676](url), what should I do to make it? Besides, if I want to use...

About data format, it is said that we can transform file, e.g., BIO-format data, into json by referring to `dataset/BC5CDR-chem/turn.py` (in the `semi_script` dir). However, this file is not available....

For example, given an input sentence "w1, w2, w3 w4", we feed it to the treeLSTM (_ChildSumTreeLSTMEncoder_), and get an encoding object. What should I do to obtain the representation...

Thank you! The script for runing test.py and the missing file. The format of the datasets in "C:\\Workspace\\FakeNews\\fake_news_data".