Reading Like HER: Human Reading Inspired Extractive Summarization

Ling Luo, Xiang Ao, Yan Song, Feiyang Pan, Min Yang, Qing He


Abstract
In this work, we re-examine the problem of extractive text summarization for long documents. We observe that the process of extracting summarization of human can be divided into two stages: 1) a rough reading stage to look for sketched information, and 2) a subsequent careful reading stage to select key sentences to form the summary. By simulating such a two-stage process, we propose a novel approach for extractive summarization. We formulate the problem as a contextual-bandit problem and solve it with policy gradient. We adopt a convolutional neural network to encode gist of paragraphs for rough reading, and a decision making policy with an adapted termination mechanism for careful reading. Experiments on the CNN and DailyMail datasets show that our proposed method can provide high-quality summaries with varied length, and significantly outperform the state-of-the-art extractive methods in terms of ROUGE metrics.
Anthology ID:
D19-1300
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3033–3043
Language:
URL:
https://aclanthology.org/D19-1300
DOI:
10.18653/v1/D19-1300
Bibkey:
Cite (ACL):
Ling Luo, Xiang Ao, Yan Song, Feiyang Pan, Min Yang, and Qing He. 2019. Reading Like HER: Human Reading Inspired Extractive Summarization. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3033–3043, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Reading Like HER: Human Reading Inspired Extractive Summarization (Luo et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1300.pdf
Attachment:
 D19-1300.Attachment.zip
Code
 LLluoling/HER
Data
CNN/Daily Mail