Automatic Keyphrase Generation by Incorporating Dual Copy Mechanisms in Sequence-to-Sequence Learning

Siyu Wang, Jianhui Jiang, Yao Huang, Yin Wang


Abstract
The keyphrase generation task is a challenging work that aims to generate a set of keyphrases for a piece of text. Many previous studies based on the sequence-to-sequence model were used to generate keyphrases, and they introduce a copy mechanism to achieve good results. However, we observed that most of the keyphrases are composed of some important words (seed words) in the source text, and if these words can be identified accurately and copied to create more keyphrases, the performance of the model might be improved. To address this challenge, we propose a DualCopyNet model, which introduces an additional sequence labeling layer for identifying seed words, and further copies the words for generating new keyphrases by dual copy mechanisms. Experimental results demonstrate that our model outperforms the baseline models and achieves an obvious performance improvement.
Anthology ID:
2022.coling-1.204
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2328–2338
Language:
URL:
https://aclanthology.org/2022.coling-1.204
DOI:
Bibkey:
Cite (ACL):
Siyu Wang, Jianhui Jiang, Yao Huang, and Yin Wang. 2022. Automatic Keyphrase Generation by Incorporating Dual Copy Mechanisms in Sequence-to-Sequence Learning. In Proceedings of the 29th International Conference on Computational Linguistics, pages 2328–2338, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Automatic Keyphrase Generation by Incorporating Dual Copy Mechanisms in Sequence-to-Sequence Learning (Wang et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.204.pdf
Data
KP20k