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 proceedingConference contribution

4 Citations (Scopus)

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 languageEnglish
Title of host publication3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings
EditorsGiuseppe Carenini, Jackie Chi Kit Cheung, Yue Dong, Fei Liu, Lu Wang
PublisherAssociation for Computational Linguistics (ACL)
Pages65-73
Number of pages9
ISBN (Electronic)9781955917049
Publication statusPublished - 2021
Event3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Virtual, Online, Dominican Republic
Duration: 2021 Nov 10 → …

Publication series

Name3rd Workshop on New Frontiers in Summarization, NewSum 2021 - Workshop Proceedings

Conference

Conference3rd Workshop on New Frontiers in Summarization, NewSum 2021
Country/TerritoryDominican Republic
CityVirtual, Online
Period21/11/10 → …

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

Fingerprint

Dive into the research topics of 'Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization'. Together they form a unique fingerprint.

Cite this