@inproceedings{roy-etal-2025-enhancing,
title = "Enhancing Textual Understanding: Automated Claim Span Identification in {E}nglish, {H}indi, {B}engali, and {C}ode{M}ix",
author = "Roy, Rudra and
Pal, Pritam and
Das, Dipankar and
Ghosh, Saptarshi and
Paul, Biswajit",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.118/",
pages = "1030--1035",
abstract = "Claim span identification, a crucial task in Natural Language Processing (NLP), aims to extract specific claims from texts. Such claim spans can be further utilized in various critical NLP applications, such as claim verification, fact-checking, and opinion mining, among others. The present work proposes a multilingual claim span identification framework for handling social media data in English, Hindi, Bengali, and CodeMixed texts, leveraging the strengths and knowledge of transformer-based pre-trained models. Our proposed framework efficiently identifies the contextual relationships between words and precisely detects claim spans across all languages, achieving a high F1 score and Jaccard score. The source code and datasets are available at: https://github.com/pritampal98/claim-span-multilingual"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roy-etal-2025-enhancing">
<titleInfo>
<title>Enhancing Textual Understanding: Automated Claim Span Identification in English, Hindi, Bengali, and CodeMix</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rudra</namePart>
<namePart type="family">Roy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pritam</namePart>
<namePart type="family">Pal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipankar</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saptarshi</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biswajit</namePart>
<namePart type="family">Paul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Claim span identification, a crucial task in Natural Language Processing (NLP), aims to extract specific claims from texts. Such claim spans can be further utilized in various critical NLP applications, such as claim verification, fact-checking, and opinion mining, among others. The present work proposes a multilingual claim span identification framework for handling social media data in English, Hindi, Bengali, and CodeMixed texts, leveraging the strengths and knowledge of transformer-based pre-trained models. Our proposed framework efficiently identifies the contextual relationships between words and precisely detects claim spans across all languages, achieving a high F1 score and Jaccard score. The source code and datasets are available at: https://github.com/pritampal98/claim-span-multilingual</abstract>
<identifier type="citekey">roy-etal-2025-enhancing</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.118/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>1030</start>
<end>1035</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Textual Understanding: Automated Claim Span Identification in English, Hindi, Bengali, and CodeMix
%A Roy, Rudra
%A Pal, Pritam
%A Das, Dipankar
%A Ghosh, Saptarshi
%A Paul, Biswajit
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F roy-etal-2025-enhancing
%X Claim span identification, a crucial task in Natural Language Processing (NLP), aims to extract specific claims from texts. Such claim spans can be further utilized in various critical NLP applications, such as claim verification, fact-checking, and opinion mining, among others. The present work proposes a multilingual claim span identification framework for handling social media data in English, Hindi, Bengali, and CodeMixed texts, leveraging the strengths and knowledge of transformer-based pre-trained models. Our proposed framework efficiently identifies the contextual relationships between words and precisely detects claim spans across all languages, achieving a high F1 score and Jaccard score. The source code and datasets are available at: https://github.com/pritampal98/claim-span-multilingual
%U https://aclanthology.org/2025.ranlp-1.118/
%P 1030-1035
Markdown (Informal)
[Enhancing Textual Understanding: Automated Claim Span Identification in English, Hindi, Bengali, and CodeMix](https://aclanthology.org/2025.ranlp-1.118/) (Roy et al., RANLP 2025)
ACL
- Rudra Roy, Pritam Pal, Dipankar Das, Saptarshi Ghosh, and Biswajit Paul. 2025. Enhancing Textual Understanding: Automated Claim Span Identification in English, Hindi, Bengali, and CodeMix. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 1030–1035, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.