@inproceedings{chen-etal-2023-improving-low,
title = "Improving Low-resource Question Answering by Augmenting Question Information",
author = "Chen, Andong and
Sun, Yuan and
Zhao, Xiaobing and
Galindo Esparza, Rosella and
Chen, Kehai and
Xiang, Yang and
Zhao, Tiejun and
Zhang, Min",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.699",
doi = "10.18653/v1/2023.findings-emnlp.699",
pages = "10413--10420",
abstract = "In the era of large models, low-resource question-answering tasks lag, emphasizing the importance of data augmentation - a key research avenue in natural language processing. The main challenges include leveraging the large model{'}s internal knowledge for data augmentation, determining which QA data component - the question, passage, or answer - benefits most from augmentation, and retaining consistency in the augmented content without inducing excessive noise. To tackle these, we introduce PQQ, an innovative approach for question data augmentation consisting of Prompt Answer, Question Generation, and Question Filter. Our experiments reveal that ChatGPT underperforms on the experimental data, yet our PQQ method excels beyond existing augmentation strategies. Further, its universal applicability is validated through successful tests on high-resource QA tasks like SQUAD1.1 and TriviaQA.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-improving-low">
<titleInfo>
<title>Improving Low-resource Question Answering by Augmenting Question Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rosella</namePart>
<namePart type="family">Galindo Esparza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kehai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiejun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the era of large models, low-resource question-answering tasks lag, emphasizing the importance of data augmentation - a key research avenue in natural language processing. The main challenges include leveraging the large model’s internal knowledge for data augmentation, determining which QA data component - the question, passage, or answer - benefits most from augmentation, and retaining consistency in the augmented content without inducing excessive noise. To tackle these, we introduce PQQ, an innovative approach for question data augmentation consisting of Prompt Answer, Question Generation, and Question Filter. Our experiments reveal that ChatGPT underperforms on the experimental data, yet our PQQ method excels beyond existing augmentation strategies. Further, its universal applicability is validated through successful tests on high-resource QA tasks like SQUAD1.1 and TriviaQA.</abstract>
<identifier type="citekey">chen-etal-2023-improving-low</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.699</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.699</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>10413</start>
<end>10420</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Low-resource Question Answering by Augmenting Question Information
%A Chen, Andong
%A Sun, Yuan
%A Zhao, Xiaobing
%A Galindo Esparza, Rosella
%A Chen, Kehai
%A Xiang, Yang
%A Zhao, Tiejun
%A Zhang, Min
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F chen-etal-2023-improving-low
%X In the era of large models, low-resource question-answering tasks lag, emphasizing the importance of data augmentation - a key research avenue in natural language processing. The main challenges include leveraging the large model’s internal knowledge for data augmentation, determining which QA data component - the question, passage, or answer - benefits most from augmentation, and retaining consistency in the augmented content without inducing excessive noise. To tackle these, we introduce PQQ, an innovative approach for question data augmentation consisting of Prompt Answer, Question Generation, and Question Filter. Our experiments reveal that ChatGPT underperforms on the experimental data, yet our PQQ method excels beyond existing augmentation strategies. Further, its universal applicability is validated through successful tests on high-resource QA tasks like SQUAD1.1 and TriviaQA.
%R 10.18653/v1/2023.findings-emnlp.699
%U https://aclanthology.org/2023.findings-emnlp.699
%U https://doi.org/10.18653/v1/2023.findings-emnlp.699
%P 10413-10420
Markdown (Informal)
[Improving Low-resource Question Answering by Augmenting Question Information](https://aclanthology.org/2023.findings-emnlp.699) (Chen et al., Findings 2023)
ACL