Keyphrase Generation with Correlation Constraints

Jun Chen, Xiaoming Zhang, Yu Wu, Zhao Yan, Zhoujun Li


Abstract
In this paper, we study automatic keyphrase generation. Although conventional approaches to this task show promising results, they neglect correlation among keyphrases, resulting in duplication and coverage issues. To solve these problems, we propose a new sequence-to-sequence architecture for keyphrase generation named CorrRNN, which captures correlation among multiple keyphrases in two ways. First, we employ a coverage vector to indicate whether the word in the source document has been summarized by previous phrases to improve the coverage for keyphrases. Second, preceding phrases are taken into account to eliminate duplicate phrases and improve result coherence. Experiment results show that our model significantly outperforms the state-of-the-art method on benchmark datasets in terms of both accuracy and diversity.
Anthology ID:
D18-1439
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4057–4066
Language:
URL:
https://aclanthology.org/D18-1439
DOI:
10.18653/v1/D18-1439
Bibkey:
Cite (ACL):
Jun Chen, Xiaoming Zhang, Yu Wu, Zhao Yan, and Zhoujun Li. 2018. Keyphrase Generation with Correlation Constraints. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4057–4066, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Keyphrase Generation with Correlation Constraints (Chen et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1439.pdf