Incorporating Linguistic Constraints into Keyphrase Generation

Jing Zhao, Yuxiang Zhang


Abstract
Keyphrases, that concisely describe the high-level topics discussed in a document, are very useful for a wide range of natural language processing tasks. Though existing keyphrase generation methods have achieved remarkable performance on this task, they generate many overlapping phrases (including sub-phrases or super-phrases) of keyphrases. In this paper, we propose the parallel Seq2Seq network with the coverage attention to alleviate the overlapping phrase problem. Specifically, we integrate the linguistic constraints of keyphrase into the basic Seq2Seq network on the source side, and employ the multi-task learning framework on the target side. In addition, in order to prevent from generating overlapping phrases of keyphrases with correct syntax, we introduce the coverage vector to keep track of the attention history and to decide whether the parts of source text have been covered by existing generated keyphrases. Experimental results show that our method can outperform the state-of-the-art CopyRNN on scientific datasets, and is also more effective in news domain.
Anthology ID:
P19-1515
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5224–5233
Language:
URL:
https://aclanthology.org/P19-1515
DOI:
10.18653/v1/P19-1515
Bibkey:
Cite (ACL):
Jing Zhao and Yuxiang Zhang. 2019. Incorporating Linguistic Constraints into Keyphrase Generation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5224–5233, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Incorporating Linguistic Constraints into Keyphrase Generation (Zhao & Zhang, ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1515.pdf
Data
KP20k
Terminologies: