@inproceedings{zou-etal-2023-towards,
title = "Towards Understanding Omission in Dialogue Summarization",
author = "Zou, Yicheng and
Song, Kaitao and
Tan, Xu and
Fu, Zhongkai and
Zhang, Qi and
Li, Dongsheng and
Gui, Tao",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.798/",
doi = "10.18653/v1/2023.acl-long.798",
pages = "14268--14286",
abstract = "Dialogue summarization aims to condense the lengthy dialogue into a concise summary, and has recently achieved significant progress. However, the result of existing methods is still far from satisfactory. Previous works indicated that omission is a major factor in affecting the quality of summarization, but few of them have further explored the omission problem, such as how omission affects summarization results and how to detect omission, which is critical for reducing omission and improving summarization quality. Moreover, analyzing and detecting omission relies on summarization datasets with omission labels (i.e., which dialogue utterances are omitted in the summarization), which are not available in the current literature. In this paper, we propose the OLDS dataset, which provides high-quality omission labels for dialogue summarization. By analyzing this dataset, we find that a large improvement in summarization quality can be achieved by providing ground-truth omission labels for the summarization model to recover omission information, which demonstrates the importance of omission detection for omission mitigation in dialogue summarization. Therefore, we formulate an omission detection task and demonstrate our proposed dataset can support the training and evaluation of this task well. We also call for research action on omission detection based on our proposed datasets. Our dataset and codes are publicly available."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zou-etal-2023-towards">
<titleInfo>
<title>Towards Understanding Omission in Dialogue Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yicheng</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaitao</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongkai</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongsheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Gui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialogue summarization aims to condense the lengthy dialogue into a concise summary, and has recently achieved significant progress. However, the result of existing methods is still far from satisfactory. Previous works indicated that omission is a major factor in affecting the quality of summarization, but few of them have further explored the omission problem, such as how omission affects summarization results and how to detect omission, which is critical for reducing omission and improving summarization quality. Moreover, analyzing and detecting omission relies on summarization datasets with omission labels (i.e., which dialogue utterances are omitted in the summarization), which are not available in the current literature. In this paper, we propose the OLDS dataset, which provides high-quality omission labels for dialogue summarization. By analyzing this dataset, we find that a large improvement in summarization quality can be achieved by providing ground-truth omission labels for the summarization model to recover omission information, which demonstrates the importance of omission detection for omission mitigation in dialogue summarization. Therefore, we formulate an omission detection task and demonstrate our proposed dataset can support the training and evaluation of this task well. We also call for research action on omission detection based on our proposed datasets. Our dataset and codes are publicly available.</abstract>
<identifier type="citekey">zou-etal-2023-towards</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.798</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.798/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>14268</start>
<end>14286</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Understanding Omission in Dialogue Summarization
%A Zou, Yicheng
%A Song, Kaitao
%A Tan, Xu
%A Fu, Zhongkai
%A Zhang, Qi
%A Li, Dongsheng
%A Gui, Tao
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zou-etal-2023-towards
%X Dialogue summarization aims to condense the lengthy dialogue into a concise summary, and has recently achieved significant progress. However, the result of existing methods is still far from satisfactory. Previous works indicated that omission is a major factor in affecting the quality of summarization, but few of them have further explored the omission problem, such as how omission affects summarization results and how to detect omission, which is critical for reducing omission and improving summarization quality. Moreover, analyzing and detecting omission relies on summarization datasets with omission labels (i.e., which dialogue utterances are omitted in the summarization), which are not available in the current literature. In this paper, we propose the OLDS dataset, which provides high-quality omission labels for dialogue summarization. By analyzing this dataset, we find that a large improvement in summarization quality can be achieved by providing ground-truth omission labels for the summarization model to recover omission information, which demonstrates the importance of omission detection for omission mitigation in dialogue summarization. Therefore, we formulate an omission detection task and demonstrate our proposed dataset can support the training and evaluation of this task well. We also call for research action on omission detection based on our proposed datasets. Our dataset and codes are publicly available.
%R 10.18653/v1/2023.acl-long.798
%U https://aclanthology.org/2023.acl-long.798/
%U https://doi.org/10.18653/v1/2023.acl-long.798
%P 14268-14286
Markdown (Informal)
[Towards Understanding Omission in Dialogue Summarization](https://aclanthology.org/2023.acl-long.798/) (Zou et al., ACL 2023)
ACL
- Yicheng Zou, Kaitao Song, Xu Tan, Zhongkai Fu, Qi Zhang, Dongsheng Li, and Tao Gui. 2023. Towards Understanding Omission in Dialogue Summarization. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14268–14286, Toronto, Canada. Association for Computational Linguistics.