@inproceedings{debnath-etal-2025-top,
title = "Top Ten from Lakhs: A Transformer-based Retrieval System for Identifying Previously Fact-Checked Claims across Multiple Languages",
author = "Debnath, Srijani and
Pal, Pritam and
Das, Dipankar",
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-1.33/",
pages = "268--274",
abstract = "The efficient identification of previously fact-checked claims across multiple languages is a challenging task. It can be time-consuming for professional fact-checkers even within a single language. It becomes much more difficult to perform manually when the claim and the fact-check may be in different languages. This paper presents a systematic approach for the retrieval of top-k relevant fact-checks for a given post in a monolingual and cross-lingual setup using two transformer-based fact-checked claim retrieval frameworks that share a common preprocessing pipeline but differ in their underlying encoder implementations: TIDE, a TensorFlow-based custom dual encoder applied to english-translated data, and PTEX, a PyTorch-based encoder operating on both english-translated and original-language inputs, and introduces a lightweight post-processing technique based on a textual feature: Keyword Overlap Count applied via reranking on top of the transformer-based frameworks. Training and evaluation on a large multilingual corpus show that the fine-tuned E5-Large-v2 model in the PTEX framework yields the best monolingual track performance, achieving an average Success@10 score of 0.8846 and the same framework model with post-processing technique achieves an average Success@10 score of 0.7393 which is the best performance in crosslingual track."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="debnath-etal-2025-top">
<titleInfo>
<title>Top Ten from Lakhs: A Transformer-based Retrieval System for Identifying Previously Fact-Checked Claims across Multiple Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Srijani</namePart>
<namePart type="family">Debnath</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>
<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>The efficient identification of previously fact-checked claims across multiple languages is a challenging task. It can be time-consuming for professional fact-checkers even within a single language. It becomes much more difficult to perform manually when the claim and the fact-check may be in different languages. This paper presents a systematic approach for the retrieval of top-k relevant fact-checks for a given post in a monolingual and cross-lingual setup using two transformer-based fact-checked claim retrieval frameworks that share a common preprocessing pipeline but differ in their underlying encoder implementations: TIDE, a TensorFlow-based custom dual encoder applied to english-translated data, and PTEX, a PyTorch-based encoder operating on both english-translated and original-language inputs, and introduces a lightweight post-processing technique based on a textual feature: Keyword Overlap Count applied via reranking on top of the transformer-based frameworks. Training and evaluation on a large multilingual corpus show that the fine-tuned E5-Large-v2 model in the PTEX framework yields the best monolingual track performance, achieving an average Success@10 score of 0.8846 and the same framework model with post-processing technique achieves an average Success@10 score of 0.7393 which is the best performance in crosslingual track.</abstract>
<identifier type="citekey">debnath-etal-2025-top</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.33/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>268</start>
<end>274</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Top Ten from Lakhs: A Transformer-based Retrieval System for Identifying Previously Fact-Checked Claims across Multiple Languages
%A Debnath, Srijani
%A Pal, Pritam
%A Das, Dipankar
%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 debnath-etal-2025-top
%X The efficient identification of previously fact-checked claims across multiple languages is a challenging task. It can be time-consuming for professional fact-checkers even within a single language. It becomes much more difficult to perform manually when the claim and the fact-check may be in different languages. This paper presents a systematic approach for the retrieval of top-k relevant fact-checks for a given post in a monolingual and cross-lingual setup using two transformer-based fact-checked claim retrieval frameworks that share a common preprocessing pipeline but differ in their underlying encoder implementations: TIDE, a TensorFlow-based custom dual encoder applied to english-translated data, and PTEX, a PyTorch-based encoder operating on both english-translated and original-language inputs, and introduces a lightweight post-processing technique based on a textual feature: Keyword Overlap Count applied via reranking on top of the transformer-based frameworks. Training and evaluation on a large multilingual corpus show that the fine-tuned E5-Large-v2 model in the PTEX framework yields the best monolingual track performance, achieving an average Success@10 score of 0.8846 and the same framework model with post-processing technique achieves an average Success@10 score of 0.7393 which is the best performance in crosslingual track.
%U https://aclanthology.org/2025.ranlp-1.33/
%P 268-274
Markdown (Informal)
[Top Ten from Lakhs: A Transformer-based Retrieval System for Identifying Previously Fact-Checked Claims across Multiple Languages](https://aclanthology.org/2025.ranlp-1.33/) (Debnath et al., RANLP 2025)
ACL