@inproceedings{gao-etal-2023-evaluating,
title = "Evaluating Factuality in Cross-lingual Summarization",
author = "Gao, Mingqi and
Wang, Wenqing and
Wan, Xiaojun and
Xu, Yuemei",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.786/",
doi = "10.18653/v1/2023.findings-acl.786",
pages = "12415--12431",
abstract = "Cross-lingual summarization aims to help people efficiently grasp the core idea of the document written in a foreign language. Modern text summarization models generate highly fluent but often factually inconsistent outputs, which has received heightened attention in recent research. However, the factual consistency of cross-lingual summarization has not been investigated yet. In this paper, we propose a cross-lingual factuality dataset by collecting human annotations of reference summaries as well as generated summaries from models at both summary level and sentence level. Furthermore, we perform the fine-grained analysis and observe that over 50{\%} of generated summaries and over 27{\%} of reference summaries contain factual errors with characteristics different from monolingual summarization. Existing evaluation metrics for monolingual summarization require translation to evaluate the factuality of cross-lingual summarization and perform differently at different tasks and levels. Finally, we adapt the monolingual factuality metrics as an initial step towards the automatic evaluation of summarization factuality in cross-lingual settings. Our dataset and code are available at \url{https://github.com/kite99520/Fact_CLS}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2023-evaluating">
<titleInfo>
<title>Evaluating Factuality in Cross-lingual Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingqi</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuemei</namePart>
<namePart type="family">Xu</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>Findings of the Association for Computational Linguistics: ACL 2023</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>Cross-lingual summarization aims to help people efficiently grasp the core idea of the document written in a foreign language. Modern text summarization models generate highly fluent but often factually inconsistent outputs, which has received heightened attention in recent research. However, the factual consistency of cross-lingual summarization has not been investigated yet. In this paper, we propose a cross-lingual factuality dataset by collecting human annotations of reference summaries as well as generated summaries from models at both summary level and sentence level. Furthermore, we perform the fine-grained analysis and observe that over 50% of generated summaries and over 27% of reference summaries contain factual errors with characteristics different from monolingual summarization. Existing evaluation metrics for monolingual summarization require translation to evaluate the factuality of cross-lingual summarization and perform differently at different tasks and levels. Finally, we adapt the monolingual factuality metrics as an initial step towards the automatic evaluation of summarization factuality in cross-lingual settings. Our dataset and code are available at https://github.com/kite99520/Fact_CLS.</abstract>
<identifier type="citekey">gao-etal-2023-evaluating</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.786</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.786/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>12415</start>
<end>12431</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Factuality in Cross-lingual Summarization
%A Gao, Mingqi
%A Wang, Wenqing
%A Wan, Xiaojun
%A Xu, Yuemei
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F gao-etal-2023-evaluating
%X Cross-lingual summarization aims to help people efficiently grasp the core idea of the document written in a foreign language. Modern text summarization models generate highly fluent but often factually inconsistent outputs, which has received heightened attention in recent research. However, the factual consistency of cross-lingual summarization has not been investigated yet. In this paper, we propose a cross-lingual factuality dataset by collecting human annotations of reference summaries as well as generated summaries from models at both summary level and sentence level. Furthermore, we perform the fine-grained analysis and observe that over 50% of generated summaries and over 27% of reference summaries contain factual errors with characteristics different from monolingual summarization. Existing evaluation metrics for monolingual summarization require translation to evaluate the factuality of cross-lingual summarization and perform differently at different tasks and levels. Finally, we adapt the monolingual factuality metrics as an initial step towards the automatic evaluation of summarization factuality in cross-lingual settings. Our dataset and code are available at https://github.com/kite99520/Fact_CLS.
%R 10.18653/v1/2023.findings-acl.786
%U https://aclanthology.org/2023.findings-acl.786/
%U https://doi.org/10.18653/v1/2023.findings-acl.786
%P 12415-12431
Markdown (Informal)
[Evaluating Factuality in Cross-lingual Summarization](https://aclanthology.org/2023.findings-acl.786/) (Gao et al., Findings 2023)
ACL
- Mingqi Gao, Wenqing Wang, Xiaojun Wan, and Yuemei Xu. 2023. Evaluating Factuality in Cross-lingual Summarization. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12415–12431, Toronto, Canada. Association for Computational Linguistics.