@inproceedings{kojima-2024-sub-table,
title = "Sub-Table Rescorer for Table Question Answering",
author = "Kojima, Atsushi",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1339",
pages = "15422--15427",
abstract = "We propose a sub-table rescorer (STR) to improve the performance of an inner table retriever (ITR)-based inference for the table question answering. Tabular language model (TLM) truncates the sequence of a long table due to their input token limits. It leads to accuracy degradation. To solve this problem, ITR extracts sub-table candidates, which correspond to a part of an entire greater original table on the basis of relevance scores to the question for each of the columns and rows. Then, the topN longest sub-tables are selected. Our proposed STR estimates the relevance score between a question and each sub-table. In this work, we explored two different methods to integrate STR to the ITR-based inference. In the first method, STR rescores sub-table candidates, and the topN sub-tables are chosen. Then, TLM outputs the most confident answer. In the second method, the score calculated by STR is interpolated with the score calculated by TLM. Then, the most confident answer is chosen. In the experiment, we evaluate the performance on the WikiTableQuestions dataset. By applying STR to the ITR-based inference, we observed 4.4{\%} and 6.3{\%} relative reductions in error rate in the rescoring- and score-fusion-based methods, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kojima-2024-sub-table">
<titleInfo>
<title>Sub-Table Rescorer for Table Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atsushi</namePart>
<namePart type="family">Kojima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a sub-table rescorer (STR) to improve the performance of an inner table retriever (ITR)-based inference for the table question answering. Tabular language model (TLM) truncates the sequence of a long table due to their input token limits. It leads to accuracy degradation. To solve this problem, ITR extracts sub-table candidates, which correspond to a part of an entire greater original table on the basis of relevance scores to the question for each of the columns and rows. Then, the topN longest sub-tables are selected. Our proposed STR estimates the relevance score between a question and each sub-table. In this work, we explored two different methods to integrate STR to the ITR-based inference. In the first method, STR rescores sub-table candidates, and the topN sub-tables are chosen. Then, TLM outputs the most confident answer. In the second method, the score calculated by STR is interpolated with the score calculated by TLM. Then, the most confident answer is chosen. In the experiment, we evaluate the performance on the WikiTableQuestions dataset. By applying STR to the ITR-based inference, we observed 4.4% and 6.3% relative reductions in error rate in the rescoring- and score-fusion-based methods, respectively.</abstract>
<identifier type="citekey">kojima-2024-sub-table</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1339</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15422</start>
<end>15427</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sub-Table Rescorer for Table Question Answering
%A Kojima, Atsushi
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F kojima-2024-sub-table
%X We propose a sub-table rescorer (STR) to improve the performance of an inner table retriever (ITR)-based inference for the table question answering. Tabular language model (TLM) truncates the sequence of a long table due to their input token limits. It leads to accuracy degradation. To solve this problem, ITR extracts sub-table candidates, which correspond to a part of an entire greater original table on the basis of relevance scores to the question for each of the columns and rows. Then, the topN longest sub-tables are selected. Our proposed STR estimates the relevance score between a question and each sub-table. In this work, we explored two different methods to integrate STR to the ITR-based inference. In the first method, STR rescores sub-table candidates, and the topN sub-tables are chosen. Then, TLM outputs the most confident answer. In the second method, the score calculated by STR is interpolated with the score calculated by TLM. Then, the most confident answer is chosen. In the experiment, we evaluate the performance on the WikiTableQuestions dataset. By applying STR to the ITR-based inference, we observed 4.4% and 6.3% relative reductions in error rate in the rescoring- and score-fusion-based methods, respectively.
%U https://aclanthology.org/2024.lrec-main.1339
%P 15422-15427
Markdown (Informal)
[Sub-Table Rescorer for Table Question Answering](https://aclanthology.org/2024.lrec-main.1339) (Kojima, LREC-COLING 2024)
ACL
- Atsushi Kojima. 2024. Sub-Table Rescorer for Table Question Answering. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15422–15427, Torino, Italia. ELRA and ICCL.