TY - GEN
T1 - Multi-document summarization with maximal marginal relevance-guided reinforcement learning
AU - Mao, Yuning
AU - Qu, Yanru
AU - Xie, Yiqing
AU - Ren, Xiang
AU - Han, Jiawei
N1 - Publisher Copyright:
© 2020 Association for Computational Linguistics
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85100545856&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85100545856&partnerID=8YFLogxK
U2 - 10.18653/v1/2020.emnlp-main.136
DO - 10.18653/v1/2020.emnlp-main.136
M3 - Conference contribution
AN - SCOPUS:85100545856
T3 - EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
SP - 1737
EP - 1751
BT - EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020
Y2 - 16 November 2020 through 20 November 2020
ER -