Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization

Dongyub Lee; Jungwoo Lim; Taesun Whang; Chanhee Lee; Seungwoo Cho; Mingun Pak; Heuiseok Lim

Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization

Dongyub Lee, Jungwoo Lim, Taesun Whang, Chanhee Lee, Seungwoo Cho, Mingun Pak, Heuiseok Lim

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

Abstract

In this paper, we focus on improving the quality of the summary generated by neural abstractive dialogue summarization systems. Even though pre-trained language models generate well-constructed and promising results, it is still challenging to summarize the conversation of multiple participants since the summary should include a description of the overall situation and the actions of each speaker. This paper proposes self-supervised strategies for speaker-focused post-correction in abstractive dialogue summarization. Specifically, our model first discriminates which type of speaker correction is required in a draft summary and then generates a revised summary according to the required type. Experimental results show that our proposed method adequately corrects the draft summaries, and the revised summaries are significantly improved in both quantitative and qualitative evaluations.

Original language	English
Title of host publication	3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings
Editors	Giuseppe Carenini, Jackie Chi Kit Cheung, Yue Dong, Fei Liu, Lu Wang
Publisher	Association for Computational Linguistics (ACL)
Pages	65-73
Number of pages	9
ISBN (Electronic)	9781955917049
Publication status	Published - 2021
Event	3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Virtual, Online, Dominican Republic Duration: 2021 Nov 10 → …

Publication series

Name	3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings

Conference

Conference	3rd Workshop on New Frontiers in Summarization, NewSum 2021
Country/Territory	Dominican Republic
City	Virtual, Online
Period	21/11/10 → …

Bibliographical note

Funding Information:
This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2018-0-01405) supervised by the IITP (Institute for Information Communications Technology Planning Evaluation).

Funding Information:
This work was supported by Institute for Information communications Technology Planning Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2020-0-00368, A Neural-Symbolic Model for Knowledge Acquisition and Inference Techniques)

Publisher Copyright:
© 2021 Association for Computational Linguistics.

ASJC Scopus subject areas

Information Systems
Computer Science Applications
Computational Theory and Mathematics

Cite this

Lee, D., Lim, J., Whang, T., Lee, C., Cho, S., Pak, M., & Lim, H. (2021). Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization. In G. Carenini, J. C. K. Cheung, Y. Dong, F. Liu, & L. Wang (Eds.), 3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings (pp. 65-73). (3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings). Association for Computational Linguistics (ACL).

Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization. / Lee, Dongyub; Lim, Jungwoo; Whang, Taesun et al.
3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings. ed. / Giuseppe Carenini; Jackie Chi Kit Cheung; Yue Dong; Fei Liu; Lu Wang. Association for Computational Linguistics (ACL), 2021. p. 65-73 (3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings).

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

Lee, D, Lim, J, Whang, T, Lee, C, Cho, S, Pak, M & Lim, H 2021, Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization. in G Carenini, JCK Cheung, Y Dong, F Liu & L Wang (eds), 3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings. 3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings, Association for Computational Linguistics (ACL), pp. 65-73, 3rd Workshop on New Frontiers in Summarization, NewSum 2021, Virtual, Online, Dominican Republic, 21/11/10.

Lee D, Lim J, Whang T, Lee C, Cho S, Pak M et al. Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization. In Carenini G, Cheung JCK, Dong Y, Liu F, Wang L, editors, 3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings. Association for Computational Linguistics (ACL). 2021. p. 65-73. (3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings).

Lee, Dongyub ; Lim, Jungwoo ; Whang, Taesun et al. / Capturing Speaker Incorrectness : Speaker-Focused Post-Correction for Abstractive Dialogue Summarization. 3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings. editor / Giuseppe Carenini ; Jackie Chi Kit Cheung ; Yue Dong ; Fei Liu ; Lu Wang. Association for Computational Linguistics (ACL), 2021. pp. 65-73 (3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings).

@inproceedings{685698dabe004a708ef37642bf077160,

title = "Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization",

abstract = "In this paper, we focus on improving the quality of the summary generated by neural abstractive dialogue summarization systems. Even though pre-trained language models generate well-constructed and promising results, it is still challenging to summarize the conversation of multiple participants since the summary should include a description of the overall situation and the actions of each speaker. This paper proposes self-supervised strategies for speaker-focused post-correction in abstractive dialogue summarization. Specifically, our model first discriminates which type of speaker correction is required in a draft summary and then generates a revised summary according to the required type. Experimental results show that our proposed method adequately corrects the draft summaries, and the revised summaries are significantly improved in both quantitative and qualitative evaluations.",

author = "Dongyub Lee and Jungwoo Lim and Taesun Whang and Chanhee Lee and Seungwoo Cho and Mingun Pak and Heuiseok Lim",

note = "Funding Information: This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2018-0-01405) supervised by the IITP (Institute for Information Communications Technology Planning Evaluation). Funding Information: This work was supported by Institute for Information communications Technology Planning Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2020-0-00368, A Neural-Symbolic Model for Knowledge Acquisition and Inference Techniques) Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics.; 3rd Workshop on New Frontiers in Summarization, NewSum 2021 ; Conference date: 10-11-2021",

year = "2021",

language = "English",

series = "3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings",

publisher = "Association for Computational Linguistics (ACL)",

pages = "65--73",

editor = "Giuseppe Carenini and Cheung, {Jackie Chi Kit} and Yue Dong and Fei Liu and Lu Wang",

booktitle = "3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings",

}

TY - GEN

T1 - Capturing Speaker Incorrectness

T2 - 3rd Workshop on New Frontiers in Summarization, NewSum 2021

AU - Lee, Dongyub

AU - Lim, Jungwoo

AU - Whang, Taesun

AU - Lee, Chanhee

AU - Cho, Seungwoo

AU - Pak, Mingun

AU - Lim, Heuiseok

N1 - Funding Information: This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2018-0-01405) supervised by the IITP (Institute for Information Communications Technology Planning Evaluation). Funding Information: This work was supported by Institute for Information communications Technology Planning Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2020-0-00368, A Neural-Symbolic Model for Knowledge Acquisition and Inference Techniques) Publisher Copyright: © 2021 Association for Computational Linguistics.

PY - 2021

Y1 - 2021

N2 - In this paper, we focus on improving the quality of the summary generated by neural abstractive dialogue summarization systems. Even though pre-trained language models generate well-constructed and promising results, it is still challenging to summarize the conversation of multiple participants since the summary should include a description of the overall situation and the actions of each speaker. This paper proposes self-supervised strategies for speaker-focused post-correction in abstractive dialogue summarization. Specifically, our model first discriminates which type of speaker correction is required in a draft summary and then generates a revised summary according to the required type. Experimental results show that our proposed method adequately corrects the draft summaries, and the revised summaries are significantly improved in both quantitative and qualitative evaluations.

AB - In this paper, we focus on improving the quality of the summary generated by neural abstractive dialogue summarization systems. Even though pre-trained language models generate well-constructed and promising results, it is still challenging to summarize the conversation of multiple participants since the summary should include a description of the overall situation and the actions of each speaker. This paper proposes self-supervised strategies for speaker-focused post-correction in abstractive dialogue summarization. Specifically, our model first discriminates which type of speaker correction is required in a draft summary and then generates a revised summary according to the required type. Experimental results show that our proposed method adequately corrects the draft summaries, and the revised summaries are significantly improved in both quantitative and qualitative evaluations.

UR - http://www.scopus.com/inward/record.url?scp=85138375249&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85138375249

T3 - 3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings

SP - 65

EP - 73

BT - 3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings

A2 - Carenini, Giuseppe

A2 - Cheung, Jackie Chi Kit

A2 - Dong, Yue

A2 - Liu, Fei

A2 - Wang, Lu

PB - Association for Computational Linguistics (ACL)

Y2 - 10 November 2021

ER -

Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this