@inproceedings{li-etal-2024-multilingual,
title = "Multilingual Generation in Abstractive Summarization: A Comparative Study",
author = "Li, Jinpeng and
Chen, Jiaze and
Chen, Huadong and
Zhao, Dongyan and
Yan, Rui",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1032",
pages = "11827--11837",
abstract = "The emergence of pre-trained models marks a significant juncture for the multilingual generation, offering unprecedented capabilities to comprehend and produce text across multiple languages. These models display commendable efficiency in high-resource languages. However, their performance notably falters in low-resource languages due to the extensive linguistic diversity encountered. Moreover, the existing works lack thorough analysis impairs the discovery of effective multilingual strategies, further complicating the advancement of current multilingual generation systems. This paper aims to appraise the efficacy of multilingual generation tasks, with a focus on summarization, through three resource availability scenarios: high-resource, low-resource, and zero-shot. We classify multilingual generation methodologies into three foundational categories based on their underlying modeling principles: Fine-tuning, Parameter-isolation, and Constraint-based approaches. Following this classification, we conduct a comprehensive comparative study of these methodologies across different resource contexts using two datasets that span six languages. This analysis provides insights into the unique advantages and limitations of each method. In addition, we introduce an innovative yet simple automatic metric LANGM designed to mitigate the prevalent problem of spurious correlations associated with language mixing. LANGM accurately measures the degree of code-mixing at the language level. Finally, we highlight several challenges and suggest potential avenues for future inquiry, aiming to spur further advancements within the field of multilingual text generation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-multilingual">
<titleInfo>
<title>Multilingual Generation in Abstractive Summarization: A Comparative Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinpeng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaze</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huadong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongyan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The emergence of pre-trained models marks a significant juncture for the multilingual generation, offering unprecedented capabilities to comprehend and produce text across multiple languages. These models display commendable efficiency in high-resource languages. However, their performance notably falters in low-resource languages due to the extensive linguistic diversity encountered. Moreover, the existing works lack thorough analysis impairs the discovery of effective multilingual strategies, further complicating the advancement of current multilingual generation systems. This paper aims to appraise the efficacy of multilingual generation tasks, with a focus on summarization, through three resource availability scenarios: high-resource, low-resource, and zero-shot. We classify multilingual generation methodologies into three foundational categories based on their underlying modeling principles: Fine-tuning, Parameter-isolation, and Constraint-based approaches. Following this classification, we conduct a comprehensive comparative study of these methodologies across different resource contexts using two datasets that span six languages. This analysis provides insights into the unique advantages and limitations of each method. In addition, we introduce an innovative yet simple automatic metric LANGM designed to mitigate the prevalent problem of spurious correlations associated with language mixing. LANGM accurately measures the degree of code-mixing at the language level. Finally, we highlight several challenges and suggest potential avenues for future inquiry, aiming to spur further advancements within the field of multilingual text generation.</abstract>
<identifier type="citekey">li-etal-2024-multilingual</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1032</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11827</start>
<end>11837</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Generation in Abstractive Summarization: A Comparative Study
%A Li, Jinpeng
%A Chen, Jiaze
%A Chen, Huadong
%A Zhao, Dongyan
%A Yan, Rui
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F li-etal-2024-multilingual
%X The emergence of pre-trained models marks a significant juncture for the multilingual generation, offering unprecedented capabilities to comprehend and produce text across multiple languages. These models display commendable efficiency in high-resource languages. However, their performance notably falters in low-resource languages due to the extensive linguistic diversity encountered. Moreover, the existing works lack thorough analysis impairs the discovery of effective multilingual strategies, further complicating the advancement of current multilingual generation systems. This paper aims to appraise the efficacy of multilingual generation tasks, with a focus on summarization, through three resource availability scenarios: high-resource, low-resource, and zero-shot. We classify multilingual generation methodologies into three foundational categories based on their underlying modeling principles: Fine-tuning, Parameter-isolation, and Constraint-based approaches. Following this classification, we conduct a comprehensive comparative study of these methodologies across different resource contexts using two datasets that span six languages. This analysis provides insights into the unique advantages and limitations of each method. In addition, we introduce an innovative yet simple automatic metric LANGM designed to mitigate the prevalent problem of spurious correlations associated with language mixing. LANGM accurately measures the degree of code-mixing at the language level. Finally, we highlight several challenges and suggest potential avenues for future inquiry, aiming to spur further advancements within the field of multilingual text generation.
%U https://aclanthology.org/2024.lrec-main.1032
%P 11827-11837
Markdown (Informal)
[Multilingual Generation in Abstractive Summarization: A Comparative Study](https://aclanthology.org/2024.lrec-main.1032) (Li et al., LREC-COLING 2024)
ACL