Standard

TabaQA at SemEval-2025 Task 8: Column Augmented Generation for Question Answering over Tabular Data. / Antropova, Ekaterina; Kratkov, Egor; Дерунец, Роман Алексеевич и др.

Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025). ред. / Sara Rosenthal; Aiala Rosá; Debanjan Ghosh; Marcos Zampieri. Vienna, Austria : Association for Computational Linguistics, 2025. стр. 937–952 2025.semeval-1.126.

Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование

Harvard

Antropova, E, Kratkov, E, Дерунец, РА, Trofimova, M, Бондаренко, И, Panchenko, A, Konovalov, V & Savkin, M 2025, TabaQA at SemEval-2025 Task 8: Column Augmented Generation for Question Answering over Tabular Data. в S Rosenthal, A Rosá, D Ghosh & M Zampieri (ред.), Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)., 2025.semeval-1.126, Association for Computational Linguistics, Vienna, Austria, стр. 937–952, The 19th International Workshop on Semantic Evaluation, Vienna, Австрия, 31.07.2025. <https://aclanthology.org/2025.semeval-1.126.pdf>

APA

Antropova, E., Kratkov, E., Дерунец, Р. А., Trofimova, M., Бондаренко, И., Panchenko, A., Konovalov, V., & Savkin, M. (2025). TabaQA at SemEval-2025 Task 8: Column Augmented Generation for Question Answering over Tabular Data. в S. Rosenthal, A. Rosá, D. Ghosh, & M. Zampieri (Ред.), Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025) (стр. 937–952). [2025.semeval-1.126] Association for Computational Linguistics. https://aclanthology.org/2025.semeval-1.126.pdf

Vancouver

Antropova E, Kratkov E, Дерунец РА, Trofimova M, Бондаренко И, Panchenko A и др. TabaQA at SemEval-2025 Task 8: Column Augmented Generation for Question Answering over Tabular Data. в Rosenthal S, Rosá A, Ghosh D, Zampieri M, Редакторы, Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025). Vienna, Austria: Association for Computational Linguistics. 2025. стр. 937–952. 2025.semeval-1.126

Author

Antropova, Ekaterina ; Kratkov, Egor ; Дерунец, Роман Алексеевич и др. / TabaQA at SemEval-2025 Task 8: Column Augmented Generation for Question Answering over Tabular Data. Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025). Редактор / Sara Rosenthal ; Aiala Rosá ; Debanjan Ghosh ; Marcos Zampieri. Vienna, Austria : Association for Computational Linguistics, 2025. стр. 937–952

BibTeX

@inproceedings{1f08182d181c4a90868dc0887a8f8971,
title = "TabaQA at SemEval-2025 Task 8: Column Augmented Generation for Question Answering over Tabular Data",
abstract = "The DataBench shared task in the SemEval-2025 competition aims to tackle the problem of QA from data in tables. Given the diversity of the structure of tables, there are different approaches to retrieving the answer. Although Retrieval-Augmented Generation (RAG) is a viable solution, extracting relevant information from tables remains challenging. In addition, the table can be prohibitively large for direct integration into the LLM context. In this paper, we address QA over tabular data first by identifying relevant columns that might contain the answers, then the LLM generates answers by providing the context of the relevant columns, and finally, the LLM refines its answers. This approach secured us 7th place in the DataBench lite category.",
author = "Ekaterina Antropova and Egor Kratkov and Дерунец, {Роман Алексеевич} and Margarita Trofimova and Иван Бондаренко and Alexander Panchenko and Vasily Konovalov and Maksim Savkin",
note = "Ekaterina Antropova, Egor Kratkov, Roman Derunets, Margarita Trofimova, Ivan Bondarenko, Alexander Panchenko, Vasily Konovalov, and Maksim Savkin. 2025. TabaQA at SemEval-2025 Task 8: Column Augmented Generation for Question Answering over Tabular Data. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 937–952, 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 = "937–952",
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 - TabaQA at SemEval-2025 Task 8: Column Augmented Generation for Question Answering over Tabular Data

AU - Antropova, Ekaterina

AU - Kratkov, Egor

AU - Дерунец, Роман Алексеевич

AU - Trofimova, Margarita

AU - Бондаренко, Иван

AU - Panchenko, Alexander

AU - Konovalov, Vasily

AU - Savkin, Maksim

N1 - Conference code: 19

PY - 2025/7

Y1 - 2025/7

N2 - The DataBench shared task in the SemEval-2025 competition aims to tackle the problem of QA from data in tables. Given the diversity of the structure of tables, there are different approaches to retrieving the answer. Although Retrieval-Augmented Generation (RAG) is a viable solution, extracting relevant information from tables remains challenging. In addition, the table can be prohibitively large for direct integration into the LLM context. In this paper, we address QA over tabular data first by identifying relevant columns that might contain the answers, then the LLM generates answers by providing the context of the relevant columns, and finally, the LLM refines its answers. This approach secured us 7th place in the DataBench lite category.

AB - The DataBench shared task in the SemEval-2025 competition aims to tackle the problem of QA from data in tables. Given the diversity of the structure of tables, there are different approaches to retrieving the answer. Although Retrieval-Augmented Generation (RAG) is a viable solution, extracting relevant information from tables remains challenging. In addition, the table can be prohibitively large for direct integration into the LLM context. In this paper, we address QA over tabular data first by identifying relevant columns that might contain the answers, then the LLM generates answers by providing the context of the relevant columns, and finally, the LLM refines its answers. This approach secured us 7th place in the DataBench lite category.

UR - https://www.scopus.com/pages/publications/105055407939

M3 - Conference contribution

SP - 937

EP - 952

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 -

ID: 85312041