@inproceedings{aryan-etal-2025-alphapro,
title = "{A}lpha{P}ro at {S}em{E}val-2025 Task 8: A Code Generation Approach for Question-Answering over Tabular Data",
author = "Aryan, Anshuman and
Wadhwa, Laukik and
Eshwar, Kalki and
Sinha, Aakarsh and
Kumar, Durgesh",
editor = "Rosenthal, Sara and
Ros{\'a}, Aiala and
Ghosh, Debanjan and
Zampieri, Marcos",
booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.semeval-1.307/",
pages = "2358--2367",
ISBN = "979-8-89176-273-2",
abstract = "This work outlines the AlphaPro team{'}s solution to SemEval-2025 Task 8: Question Answering on Tabular Data. Our system utilizes a three-stage pipeline that uses natural language questions along with the table{'}s structural information to generate executable Python code, which is subsequently used to query the table and produce answers. The method achieves up to 67{\%} accuracy in task data, demonstrating the feasibility of code generation for tabular question answering. The strengths and limitations of the approach are outlined and suggestions for further research are provided. The code has been made available in a public code repository to promote reproducibility and research in this area."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aryan-etal-2025-alphapro">
<titleInfo>
<title>AlphaPro at SemEval-2025 Task 8: A Code Generation Approach for Question-Answering over Tabular Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anshuman</namePart>
<namePart type="family">Aryan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laukik</namePart>
<namePart type="family">Wadhwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalki</namePart>
<namePart type="family">Eshwar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakarsh</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Durgesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-273-2</identifier>
</relatedItem>
<abstract>This work outlines the AlphaPro team’s solution to SemEval-2025 Task 8: Question Answering on Tabular Data. Our system utilizes a three-stage pipeline that uses natural language questions along with the table’s structural information to generate executable Python code, which is subsequently used to query the table and produce answers. The method achieves up to 67% accuracy in task data, demonstrating the feasibility of code generation for tabular question answering. The strengths and limitations of the approach are outlined and suggestions for further research are provided. The code has been made available in a public code repository to promote reproducibility and research in this area.</abstract>
<identifier type="citekey">aryan-etal-2025-alphapro</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.307/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2358</start>
<end>2367</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AlphaPro at SemEval-2025 Task 8: A Code Generation Approach for Question-Answering over Tabular Data
%A Aryan, Anshuman
%A Wadhwa, Laukik
%A Eshwar, Kalki
%A Sinha, Aakarsh
%A Kumar, Durgesh
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F aryan-etal-2025-alphapro
%X This work outlines the AlphaPro team’s solution to SemEval-2025 Task 8: Question Answering on Tabular Data. Our system utilizes a three-stage pipeline that uses natural language questions along with the table’s structural information to generate executable Python code, which is subsequently used to query the table and produce answers. The method achieves up to 67% accuracy in task data, demonstrating the feasibility of code generation for tabular question answering. The strengths and limitations of the approach are outlined and suggestions for further research are provided. The code has been made available in a public code repository to promote reproducibility and research in this area.
%U https://aclanthology.org/2025.semeval-1.307/
%P 2358-2367
Markdown (Informal)
[AlphaPro at SemEval-2025 Task 8: A Code Generation Approach for Question-Answering over Tabular Data](https://aclanthology.org/2025.semeval-1.307/) (Aryan et al., SemEval 2025)
ACL