@inproceedings{takatsuka-etal-2022-phrase,
title = "Phrase-Level Localization of Inconsistency Errors in Summarization by Weak Supervision",
author = "Takatsuka, Masato and
Kobayashi, Tetsunori and
Hayashi, Yoshihiko",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.537/",
pages = "6151--6164",
abstract = "Although the fluency of automatically generated abstractive summaries has improved significantly with advanced methods, the inconsistency that remains in summarization is recognized as an issue to be addressed. In this study, we propose a methodology for localizing inconsistency errors in summarization. A synthetic dataset that contains a variety of factual errors likely to be produced by a common summarizer is created by applying sentence fusion, compression, and paraphrasing operations. In creating the dataset, we automatically label erroneous phrases and the dependency relations between them as {\textquotedblleft}inconsistent,{\textquotedblright} which can contribute to detecting errors more adequately than existing models that rely only on dependency arc-level labels. Subsequently, this synthetic dataset is employed as weak supervision to train a model called SumPhrase, which jointly localizes errors in a summary and their corresponding sentences in the source document. The empirical results demonstrate that our SumPhrase model can detect factual errors in summarization more effectively than existing weakly supervised methods owing to the phrase-level labeling. Moreover, the joint identification of error-corresponding original sentences is proven to be effective in improving error detection accuracy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takatsuka-etal-2022-phrase">
<titleInfo>
<title>Phrase-Level Localization of Inconsistency Errors in Summarization by Weak Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masato</namePart>
<namePart type="family">Takatsuka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tetsunori</namePart>
<namePart type="family">Kobayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshihiko</namePart>
<namePart type="family">Hayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although the fluency of automatically generated abstractive summaries has improved significantly with advanced methods, the inconsistency that remains in summarization is recognized as an issue to be addressed. In this study, we propose a methodology for localizing inconsistency errors in summarization. A synthetic dataset that contains a variety of factual errors likely to be produced by a common summarizer is created by applying sentence fusion, compression, and paraphrasing operations. In creating the dataset, we automatically label erroneous phrases and the dependency relations between them as “inconsistent,” which can contribute to detecting errors more adequately than existing models that rely only on dependency arc-level labels. Subsequently, this synthetic dataset is employed as weak supervision to train a model called SumPhrase, which jointly localizes errors in a summary and their corresponding sentences in the source document. The empirical results demonstrate that our SumPhrase model can detect factual errors in summarization more effectively than existing weakly supervised methods owing to the phrase-level labeling. Moreover, the joint identification of error-corresponding original sentences is proven to be effective in improving error detection accuracy.</abstract>
<identifier type="citekey">takatsuka-etal-2022-phrase</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.537/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>6151</start>
<end>6164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Phrase-Level Localization of Inconsistency Errors in Summarization by Weak Supervision
%A Takatsuka, Masato
%A Kobayashi, Tetsunori
%A Hayashi, Yoshihiko
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F takatsuka-etal-2022-phrase
%X Although the fluency of automatically generated abstractive summaries has improved significantly with advanced methods, the inconsistency that remains in summarization is recognized as an issue to be addressed. In this study, we propose a methodology for localizing inconsistency errors in summarization. A synthetic dataset that contains a variety of factual errors likely to be produced by a common summarizer is created by applying sentence fusion, compression, and paraphrasing operations. In creating the dataset, we automatically label erroneous phrases and the dependency relations between them as “inconsistent,” which can contribute to detecting errors more adequately than existing models that rely only on dependency arc-level labels. Subsequently, this synthetic dataset is employed as weak supervision to train a model called SumPhrase, which jointly localizes errors in a summary and their corresponding sentences in the source document. The empirical results demonstrate that our SumPhrase model can detect factual errors in summarization more effectively than existing weakly supervised methods owing to the phrase-level labeling. Moreover, the joint identification of error-corresponding original sentences is proven to be effective in improving error detection accuracy.
%U https://aclanthology.org/2022.coling-1.537/
%P 6151-6164
Markdown (Informal)
[Phrase-Level Localization of Inconsistency Errors in Summarization by Weak Supervision](https://aclanthology.org/2022.coling-1.537/) (Takatsuka et al., COLING 2022)
ACL