Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning

Yuning Mao, Yanru Qu, Yiqing Xie, Xiang Ren, Jiawei Han


Abstract
While neural sequence learning methods have made significant progress in single-document summarization (SDS), they produce unsatisfactory results on multi-document summarization (MDS). We observe two major challenges when adapting SDS advances to MDS: (1) MDS involves larger search space and yet more limited training data, setting obstacles for neural methods to learn adequate representations; (2) MDS needs to resolve higher information redundancy among the source documents, which SDS methods are less effective to handle. To close the gap, we present RL-MMR, Maximal Margin Relevance-guided Reinforcement Learning for MDS, which unifies advanced neural SDS methods and statistical measures used in classical MDS. RL-MMR casts MMR guidance on fewer promising candidates, which restrains the search space and thus leads to better representation learning. Additionally, the explicit redundancy measure in MMR helps the neural representation of the summary to better capture redundancy. Extensive experiments demonstrate that RL-MMR achieves state-of-the-art performance on benchmark MDS datasets. In particular, we show the benefits of incorporating MMR into end-to-end learning when adapting SDS to MDS in terms of both learning effectiveness and efficiency.
Anthology ID:
2020.emnlp-main.136
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1737–1751
Language:
URL:
https://aclanthology.org/2020.emnlp-main.136
DOI:
10.18653/v1/2020.emnlp-main.136
Bibkey:
Cite (ACL):
Yuning Mao, Yanru Qu, Yiqing Xie, Xiang Ren, and Jiawei Han. 2020. Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1737–1751, Online. Association for Computational Linguistics.
Cite (Informal):
Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning (Mao et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2020.emnlp-main.136.pdf
Video:
 https://slideslive.com/38938676
Code
 morningmoni/RL-MMR