@inproceedings{mouravieff-etal-2024-learning,
title = "Learning Relational Decomposition of Queries for Question Answering from Tables",
author = {Mouravieff, Rapha{\"e}l and
Piwowarski, Benjamin and
Lamprier, Sylvain},
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.564",
doi = "10.18653/v1/2024.acl-long.564",
pages = "10471--10485",
abstract = "Table Question-Answering involves both understanding the natural language query and grounding it in the context of the input table to extract relevant information. In this context, many methods have highlighted the benefits of intermediate pre-training using SQL queries. However, while most approaches aim at generating final answers directly from inputs, we claim that there is better to do with SQL queries during training.By learning to imitate a restricted subset of SQL-like algebraic operations, we demonstrate that their execution flow provides intermediate supervision steps that allow for increased generalization and structural reasoning compared to classical approaches. Our method, bridges the gap between semantic parsing and direct answering methods, offering valuable insights into which types of operations should be predicted by a generative architecture and which should be executed by an external algorithm. Our code can be found at https://github.com/RaphaelMouravieff/Partial-Exec.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mouravieff-etal-2024-learning">
<titleInfo>
<title>Learning Relational Decomposition of Queries for Question Answering from Tables</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raphaël</namePart>
<namePart type="family">Mouravieff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Piwowarski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylvain</namePart>
<namePart type="family">Lamprier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Table Question-Answering involves both understanding the natural language query and grounding it in the context of the input table to extract relevant information. In this context, many methods have highlighted the benefits of intermediate pre-training using SQL queries. However, while most approaches aim at generating final answers directly from inputs, we claim that there is better to do with SQL queries during training.By learning to imitate a restricted subset of SQL-like algebraic operations, we demonstrate that their execution flow provides intermediate supervision steps that allow for increased generalization and structural reasoning compared to classical approaches. Our method, bridges the gap between semantic parsing and direct answering methods, offering valuable insights into which types of operations should be predicted by a generative architecture and which should be executed by an external algorithm. Our code can be found at https://github.com/RaphaelMouravieff/Partial-Exec.</abstract>
<identifier type="citekey">mouravieff-etal-2024-learning</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.564</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.564</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>10471</start>
<end>10485</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Relational Decomposition of Queries for Question Answering from Tables
%A Mouravieff, Raphaël
%A Piwowarski, Benjamin
%A Lamprier, Sylvain
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F mouravieff-etal-2024-learning
%X Table Question-Answering involves both understanding the natural language query and grounding it in the context of the input table to extract relevant information. In this context, many methods have highlighted the benefits of intermediate pre-training using SQL queries. However, while most approaches aim at generating final answers directly from inputs, we claim that there is better to do with SQL queries during training.By learning to imitate a restricted subset of SQL-like algebraic operations, we demonstrate that their execution flow provides intermediate supervision steps that allow for increased generalization and structural reasoning compared to classical approaches. Our method, bridges the gap between semantic parsing and direct answering methods, offering valuable insights into which types of operations should be predicted by a generative architecture and which should be executed by an external algorithm. Our code can be found at https://github.com/RaphaelMouravieff/Partial-Exec.
%R 10.18653/v1/2024.acl-long.564
%U https://aclanthology.org/2024.acl-long.564
%U https://doi.org/10.18653/v1/2024.acl-long.564
%P 10471-10485
Markdown (Informal)
[Learning Relational Decomposition of Queries for Question Answering from Tables](https://aclanthology.org/2024.acl-long.564) (Mouravieff et al., ACL 2024)
ACL