Xiang Dai

'Sentences with discontinuous mentions' and 'Discontinuous mentions only' are different. 'Evaluating Discontinuous mentions only ' looks like ~~~ for p in predictions: if p is not discontinuous mention: continue if...

I didn't get what other two models are? you mean baseline models?

I guess it is always better to have more strong baselines :) Considering the popularity of BERT, you may even want to BERize these baselines (for now, one is using...

Hi, if I understand your question correctly, you are asking whether two entities (t1 t4 and t4 t1) are the same (here assuming t1 t2 t3 t4 is a sequence...

Hi, I am not sure what do you mean by saying 'implementing'. Are you reimplement using your code base? or you just run my code? If later, this [issue](https://github.com/daixiangau/acl2020-transition-discontinuous-ner/issues/3) may...

Hi, there is a train.log in that issue, maybe get some clues by comparing yours and that one?

sorry I cannot direcly share the data. But happy to help if you have problems regarding download and preprocessing.

Hi, these two links may help: https://github.com/daixiangau/acl2020-transition-discontinuous-ner/blob/master/data/share2013/script.sh https://github.com/daixiangau/acl2020-transition-discontinuous-ner/blob/master/data/share2014/script.sh

Hi, Here is the description from our paper: > As CADEC does not have an official train-test split, we follow Metke-Jimenez and Karimi (2016) and randomly assign 70% of the...

Hi just want to make sure are you using https://github.com/daixiangau/acl2020-transition-discontinuous-ner/blob/master/data/cadec/build_data_for_transition_discontinuous_ner.sh? If i remember correctly, when you run convert_text_inline.py, you can set whether to add `Document:', the default should be (no_doc_info...