search

VioletPeng / GraphLSTM_release

Implementation of TACL 2017 paper: Cross-Sentence N-ary Relation Extraction with Graph LSTMs. Nanyun Peng, Hoifung Poon, Chris Quirk, Kristina Toutanova and Wen-tau Yih.
61 stars 19 forks source link

Discourse relation #1

Closed wt123u closed 4 years ago

wt123u commented 5 years ago

@VioletPeng Hi, Thanks for sharing! Is the discourse relation used in the code? If so, what is the markup? Since both the dependency relation and the discourse relation are dependencies in the data_graph, it is a little confusing about the discourse relation.

VioletPeng commented 5 years ago

Hi, as we discussed in the paper, the discourse relation wasn't included. We tried it in the early stage of the development and found it not useful (probably because it's too noisy)

wt123u commented 5 years ago

Hi, Thank you for your quick reply. I would like to add discourse relation to cross-sentence relation extraction. Could you give me some suggestions? Since I find that performance degrades when dependency information is added, I want to try the discourse relation.