Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards

Hou Pong Chan, Wang Chen, Lu Wang, Irwin King


Abstract
Generating keyphrases that summarize the main points of a document is a fundamental task in natural language processing. Although existing generative models are capable of predicting multiple keyphrases for an input document as well as determining the number of keyphrases to generate, they still suffer from the problem of generating too few keyphrases. To address this problem, we propose a reinforcement learning (RL) approach for keyphrase generation, with an adaptive reward function that encourages a model to generate both sufficient and accurate keyphrases. Furthermore, we introduce a new evaluation method that incorporates name variations of the ground-truth keyphrases using the Wikipedia knowledge base. Thus, our evaluation method can more robustly evaluate the quality of predicted keyphrases. Extensive experiments on five real-world datasets of different scales demonstrate that our RL approach consistently and significantly improves the performance of the state-of-the-art generative models with both conventional and new evaluation methods.
Anthology ID:
P19-1208
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2163–2174
Language:
URL:
https://aclanthology.org/P19-1208
DOI:
10.18653/v1/P19-1208
Bibkey:
Cite (ACL):
Hou Pong Chan, Wang Chen, Lu Wang, and Irwin King. 2019. Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2163–2174, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards (Chan et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1208.pdf
Code
 kenchan0226/keyphrase-generation-rl
Data
KP20k