Standard
Harvard
Nikolaev, E
, Бондаренко, И, Aushev, I, Krikunov, V, Glinskii, A, Konovalov, V & Belikova, J 2025,
FactDebug at SemEval-2025 Task 7: Hybrid Retrieval Pipeline for Identifying Previously Fact-Checked Claims Across Multiple Languages. in S Rosenthal, A Rosá, D Ghosh & M Zampieri (eds),
Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)., 2025.semeval-1.284, Association for Computational Linguistics, Vienna, Austria, pp. 2190–2196, The 19th International Workshop on Semantic Evaluation, Vienna, Austria,
31.07.2025. <
https://aclanthology.org/2025.semeval-1.284.pdf>
APA
Nikolaev, E.
, Бондаренко, И., Aushev, I., Krikunov, V., Glinskii, A., Konovalov, V., & Belikova, J. (2025).
FactDebug at SemEval-2025 Task 7: Hybrid Retrieval Pipeline for Identifying Previously Fact-Checked Claims Across Multiple Languages. In S. Rosenthal, A. Rosá, D. Ghosh, & M. Zampieri (Eds.),
Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025) (pp. 2190–2196). [2025.semeval-1.284] Association for Computational Linguistics.
https://aclanthology.org/2025.semeval-1.284.pdf
Vancouver
Nikolaev E
, Бондаренко И, Aushev I, Krikunov V, Glinskii A, Konovalov V et al.
FactDebug at SemEval-2025 Task 7: Hybrid Retrieval Pipeline for Identifying Previously Fact-Checked Claims Across Multiple Languages. In Rosenthal S, Rosá A, Ghosh D, Zampieri M, editors, Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025). Vienna, Austria: Association for Computational Linguistics. 2025. p. 2190–2196. 2025.semeval-1.284
Author
BibTeX
@inproceedings{f42ddecc45274ec0bc550b637d01d78d,
title = "FactDebug at SemEval-2025 Task 7: Hybrid Retrieval Pipeline for Identifying Previously Fact-Checked Claims Across Multiple Languages",
abstract = "The proliferation of multilingual misinformation demands robust systems for crosslingual fact-checked claim retrieval. This paper addresses SemEval-2025 Shared Task 7, which challenges participants to retrieve fact-checks for social media posts across 14 languages, even when posts and fact-checks are in different languages. We propose a hybrid retrieval pipeline that combines sparse lexical matching (BM25, BGE-m3) and dense semantic retrieval (pretrained and fine-tuned BGE-m3) with dynamic fusion and curriculum-trained rerankers. Our system achieves 67.2% crosslingual and 86.01% monolingual accuracy on the Shared Task MultiClaim dataset.",
author = "Evgenii Nikolaev and Иван Бондаренко and Islam Aushev and Vasilii Krikunov and Andrei Glinskii and Vasily Konovalov and Julia Belikova",
note = "Evgenii Nikolaev, Ivan Bondarenko, Islam Aushev, Vasilii Krikunov, Andrei Glinskii, Vasily Konovalov, and Julia Belikova. 2025. FactDebug at SemEval-2025 Task 7: Hybrid Retrieval Pipeline for Identifying Previously Fact-Checked Claims Across Multiple Languages. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2190–2196, Vienna, Austria. Association for Computational Linguistics.; The 19th International Workshop on Semantic Evaluation, SemEval 2025 ; Conference date: 31-07-2025 Through 01-08-2025",
year = "2025",
month = jul,
language = "English",
pages = "2190–2196",
editor = "Sara Rosenthal and Aiala Ros{\'a} and Debanjan Ghosh and Marcos Zampieri",
booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
publisher = "Association for Computational Linguistics",
address = "United States",
}
RIS
TY - GEN
T1 - FactDebug at SemEval-2025 Task 7: Hybrid Retrieval Pipeline for Identifying Previously Fact-Checked Claims Across Multiple Languages
AU - Nikolaev, Evgenii
AU - Бондаренко, Иван
AU - Aushev, Islam
AU - Krikunov, Vasilii
AU - Glinskii, Andrei
AU - Konovalov, Vasily
AU - Belikova, Julia
N1 - Conference code: 19
PY - 2025/7
Y1 - 2025/7
N2 - The proliferation of multilingual misinformation demands robust systems for crosslingual fact-checked claim retrieval. This paper addresses SemEval-2025 Shared Task 7, which challenges participants to retrieve fact-checks for social media posts across 14 languages, even when posts and fact-checks are in different languages. We propose a hybrid retrieval pipeline that combines sparse lexical matching (BM25, BGE-m3) and dense semantic retrieval (pretrained and fine-tuned BGE-m3) with dynamic fusion and curriculum-trained rerankers. Our system achieves 67.2% crosslingual and 86.01% monolingual accuracy on the Shared Task MultiClaim dataset.
AB - The proliferation of multilingual misinformation demands robust systems for crosslingual fact-checked claim retrieval. This paper addresses SemEval-2025 Shared Task 7, which challenges participants to retrieve fact-checks for social media posts across 14 languages, even when posts and fact-checks are in different languages. We propose a hybrid retrieval pipeline that combines sparse lexical matching (BM25, BGE-m3) and dense semantic retrieval (pretrained and fine-tuned BGE-m3) with dynamic fusion and curriculum-trained rerankers. Our system achieves 67.2% crosslingual and 86.01% monolingual accuracy on the Shared Task MultiClaim dataset.
UR - https://www.scopus.com/pages/publications/105055480562
M3 - Conference contribution
SP - 2190
EP - 2196
BT - Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
A2 - Rosenthal, Sara
A2 - Rosá, Aiala
A2 - Ghosh, Debanjan
A2 - Zampieri, Marcos
PB - Association for Computational Linguistics
CY - Vienna, Austria
T2 - The 19th International Workshop on Semantic Evaluation
Y2 - 31 July 2025 through 1 August 2025
ER -