Abstractive Summarization with the Aid of Extractive Summarization

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

2 Scopus Citations
View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationWeb and Big Data
Subtitle of host publicationSecond International Joint Conference, APWeb-WAIM 2018, Proceedings
EditorsYi Cai, Yoshiharu Ishikawa, Jianliang Xu
PublisherSpringer, Cham
Pages3-15
Volume1
ISBN (Electronic)9783319968902
ISBN (Print)9783319968896
Publication statusPublished - Jul 2018

Publication series

NameLecture Notes in Computer Science (including subseries Information Systems and Applications, incl. Internet/Web, and HCI)
PublisherSpringer, Cham
VolumeLNCS 10987
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Title2nd Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data, APWeb-WAIM 2018
PlaceMacao
Period23 - 25 July 2018

Abstract

Currently the abstractive method and extractive method are two main approaches for automatic document summarization. To fully integrate the relatedness and advantages of both approaches, we propose in this paper a general framework for abstractive summarization which incorporates extractive summarization as an auxiliary task. In particular, our framework is composed of a shared hierarchical document encoder, an attention-based decoder for abstractive summarization, and an extractor for sentence-level extractive summarization. Learning these two tasks jointly with the shared encoder allows us to better capture the semantics in the document. Moreover, we constrain the attention learned in the abstractive task by the salience estimated in the extractive task to strengthen their consistency. Experiments on the CNN/DailyMail dataset demonstrate that both the auxiliary task and the attention constraint contribute to improve the performance significantly, and our model is comparable to the state-of-the-art abstractive models.

Research Area(s)

  • Abstractive document summarization, Joint learning, Squence-to-sequence

Bibliographic Note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Citation Format(s)

Abstractive Summarization with the Aid of Extractive Summarization. / Chen, Yangbin; Ma, Yun; Mao, Xudong et al.
Web and Big Data: Second International Joint Conference, APWeb-WAIM 2018, Proceedings. ed. / Yi Cai; Yoshiharu Ishikawa; Jianliang Xu. Vol. 1 Springer, Cham, 2018. p. 3-15 (Lecture Notes in Computer Science (including subseries Information Systems and Applications, incl. Internet/Web, and HCI); Vol. LNCS 10987).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review