@inproceedings{unlu-menevse-etal-2024-dealing-data,
title = "Dealing with Data Scarcity in Spoken Question Answering",
author = {{\"U}nl{\"u} Menev{\c{s}}e, Merve and
Manav, Yusufcan and
Arisoy, Ebru and
{\"O}zg{\"u}r, Arzucan},
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.397",
pages = "4449--4455",
abstract = "This paper focuses on dealing with data scarcity in spoken question answering (QA) using automatic question-answer generation and a carefully selected fine-tuning strategy that leverages limited annotated data (paragraphs and question-answer pairs). Spoken QA is a challenging task due to using spoken documents, i.e., erroneous automatic speech recognition (ASR) transcriptions, and the scarcity of spoken QA data. We propose a framework for utilizing limited annotated data effectively to improve spoken QA performance. To deal with data scarcity, we train a question-answer generation model with annotated data and then produce large amounts of question-answer pairs from unannotated data (paragraphs). Our experiments demonstrate that incorporating limited annotated data and the automatically generated data through a carefully selected fine-tuning strategy leads to 5.5{\%} relative F1 gain over the model trained only with annotated data. Moreover, the proposed framework is also effective in high ASR errors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="unlu-menevse-etal-2024-dealing-data">
<titleInfo>
<title>Dealing with Data Scarcity in Spoken Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Merve</namePart>
<namePart type="family">Ünlü Menevşe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusufcan</namePart>
<namePart type="family">Manav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ebru</namePart>
<namePart type="family">Arisoy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arzucan</namePart>
<namePart type="family">Özgür</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>This paper focuses on dealing with data scarcity in spoken question answering (QA) using automatic question-answer generation and a carefully selected fine-tuning strategy that leverages limited annotated data (paragraphs and question-answer pairs). Spoken QA is a challenging task due to using spoken documents, i.e., erroneous automatic speech recognition (ASR) transcriptions, and the scarcity of spoken QA data. We propose a framework for utilizing limited annotated data effectively to improve spoken QA performance. To deal with data scarcity, we train a question-answer generation model with annotated data and then produce large amounts of question-answer pairs from unannotated data (paragraphs). Our experiments demonstrate that incorporating limited annotated data and the automatically generated data through a carefully selected fine-tuning strategy leads to 5.5% relative F1 gain over the model trained only with annotated data. Moreover, the proposed framework is also effective in high ASR errors.</abstract>
<identifier type="citekey">unlu-menevse-etal-2024-dealing-data</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.397</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4449</start>
<end>4455</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dealing with Data Scarcity in Spoken Question Answering
%A Ünlü Menevşe, Merve
%A Manav, Yusufcan
%A Arisoy, Ebru
%A Özgür, Arzucan
%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 unlu-menevse-etal-2024-dealing-data
%X This paper focuses on dealing with data scarcity in spoken question answering (QA) using automatic question-answer generation and a carefully selected fine-tuning strategy that leverages limited annotated data (paragraphs and question-answer pairs). Spoken QA is a challenging task due to using spoken documents, i.e., erroneous automatic speech recognition (ASR) transcriptions, and the scarcity of spoken QA data. We propose a framework for utilizing limited annotated data effectively to improve spoken QA performance. To deal with data scarcity, we train a question-answer generation model with annotated data and then produce large amounts of question-answer pairs from unannotated data (paragraphs). Our experiments demonstrate that incorporating limited annotated data and the automatically generated data through a carefully selected fine-tuning strategy leads to 5.5% relative F1 gain over the model trained only with annotated data. Moreover, the proposed framework is also effective in high ASR errors.
%U https://aclanthology.org/2024.lrec-main.397
%P 4449-4455
Markdown (Informal)
[Dealing with Data Scarcity in Spoken Question Answering](https://aclanthology.org/2024.lrec-main.397) (Ünlü Menevşe et al., LREC-COLING 2024)
ACL
- Merve Ünlü Menevşe, Yusufcan Manav, Ebru Arisoy, and Arzucan Özgür. 2024. Dealing with Data Scarcity in Spoken Question Answering. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4449–4455, Torino, Italia. ELRA and ICCL.