Papers with overlapping phrase problem

1 papers
Incorporating Linguistic Constraints into Keyphrase Generation (P19-1)

Copied to clipboard

Challenge: Existing keyphrase generation methods generate overlapping phrases (including sub-phrases or super-phrase) Existing methods are far from satisfactory for a wide range of natural language processing tasks.
Approach: They propose a parallel Seq2Seq network with coverage attention to alleviate the overlapping phrase problem by integrating linguistic constraints of keyphrase into the basic Seq2-Sequeq network on the source side and employ the multi-task learning framework on the target side.
Outcome: The proposed method outperforms the state-of-the-art CopyRNN on scientific datasets and is also more effective in news domain.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations