Abstractive summarization by neural attention model with document content memory

Yunseok Choi; Dahae Kim; Jee Hyong Lee

doi:10.1145/3264746.3264773

Abstractive summarization by neural attention model with document content memory

Sungkyunkwan University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

In this paper, we propose a generative approach for abstractive summarization, which creates summaries based on a language model. The main goal of our paper is to generate a long sequence of words with coherent sentences by reflecting the key concepts of the original document and the characteristics of summaries. To achieve this goal, we propose an attention mechanism that uses Document Content Memory for learning the language model effectively. To evaluate its effectiveness, the proposed methods are compared with other language models and an extractive summarization method. The results demonstrated that the proposed methods could be competitive with other approaches.

Original language	English
Title of host publication	Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018
Publisher	Association for Computing Machinery, Inc
Pages	11-16
Number of pages	6
ISBN (Electronic)	9781450358859
DOIs	https://doi.org/10.1145/3264746.3264773
State	Published - 9 Oct 2018
Event	2018 Conference Research in Adaptive and Convergent Systems, RACS 2018 - Honolulu, United States Duration: 9 Oct 2018 → 12 Oct 2018

Publication series

Name	Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018

Conference

Conference	2018 Conference Research in Adaptive and Convergent Systems, RACS 2018
Country/Territory	United States
City	Honolulu
Period	9/10/18 → 12/10/18

Keywords

Abstractive summarization
Attention mechanism
Document Content Memory
Generative approach
Language model

Access to Document

10.1145/3264746.3264773

Cite this

Choi, Y., Kim, D., & Lee, J. H. (2018). Abstractive summarization by neural attention model with document content memory. In Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018 (pp. 11-16). (Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018). Association for Computing Machinery, Inc. https://doi.org/10.1145/3264746.3264773

@inproceedings{8b8fb260b0104393bf42dd84ca427128,

title = "Abstractive summarization by neural attention model with document content memory",

abstract = "In this paper, we propose a generative approach for abstractive summarization, which creates summaries based on a language model. The main goal of our paper is to generate a long sequence of words with coherent sentences by reflecting the key concepts of the original document and the characteristics of summaries. To achieve this goal, we propose an attention mechanism that uses Document Content Memory for learning the language model effectively. To evaluate its effectiveness, the proposed methods are compared with other language models and an extractive summarization method. The results demonstrated that the proposed methods could be competitive with other approaches.",

keywords = "Abstractive summarization, Attention mechanism, Document Content Memory, Generative approach, Language model",

author = "Yunseok Choi and Dahae Kim and Lee, \{Jee Hyong\}",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 2018 Conference Research in Adaptive and Convergent Systems, RACS 2018 ; Conference date: 09-10-2018 Through 12-10-2018",

year = "2018",

month = oct,

day = "9",

doi = "10.1145/3264746.3264773",

language = "English",

series = "Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018",

publisher = "Association for Computing Machinery, Inc",

pages = "11--16",

booktitle = "Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018",

}

Choi, Y, Kim, D & Lee, JH 2018, Abstractive summarization by neural attention model with document content memory. in Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018. Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018, Association for Computing Machinery, Inc, pp. 11-16, 2018 Conference Research in Adaptive and Convergent Systems, RACS 2018, Honolulu, United States, 9/10/18. https://doi.org/10.1145/3264746.3264773

Abstractive summarization by neural attention model with document content memory. / Choi, Yunseok; Kim, Dahae; Lee, Jee Hyong.
Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018. Association for Computing Machinery, Inc, 2018. p. 11-16 (Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Abstractive summarization by neural attention model with document content memory

AU - Choi, Yunseok

AU - Kim, Dahae

AU - Lee, Jee Hyong

PY - 2018/10/9

Y1 - 2018/10/9

N2 - In this paper, we propose a generative approach for abstractive summarization, which creates summaries based on a language model. The main goal of our paper is to generate a long sequence of words with coherent sentences by reflecting the key concepts of the original document and the characteristics of summaries. To achieve this goal, we propose an attention mechanism that uses Document Content Memory for learning the language model effectively. To evaluate its effectiveness, the proposed methods are compared with other language models and an extractive summarization method. The results demonstrated that the proposed methods could be competitive with other approaches.

AB - In this paper, we propose a generative approach for abstractive summarization, which creates summaries based on a language model. The main goal of our paper is to generate a long sequence of words with coherent sentences by reflecting the key concepts of the original document and the characteristics of summaries. To achieve this goal, we propose an attention mechanism that uses Document Content Memory for learning the language model effectively. To evaluate its effectiveness, the proposed methods are compared with other language models and an extractive summarization method. The results demonstrated that the proposed methods could be competitive with other approaches.

KW - Abstractive summarization

KW - Attention mechanism

KW - Document Content Memory

KW - Generative approach

KW - Language model

UR - https://www.scopus.com/pages/publications/85056858154

U2 - 10.1145/3264746.3264773

DO - 10.1145/3264746.3264773

M3 - Conference contribution

AN - SCOPUS:85056858154

T3 - Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018

SP - 11

EP - 16

BT - Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018

PB - Association for Computing Machinery, Inc

T2 - 2018 Conference Research in Adaptive and Convergent Systems, RACS 2018

Y2 - 9 October 2018 through 12 October 2018

ER -

Abstractive summarization by neural attention model with document content memory

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this