@inproceedings{huber-etal-2022-ccqa,
title = "{CCQA}: A New Web-Scale Question Answering Dataset for Model Pre-Training",
author = "Huber, Patrick and
Aghajanyan, Armen and
Oguz, Barlas and
Okhonko, Dmytro and
Yih, Scott and
Gupta, Sonal and
Chen, Xilun",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.184",
doi = "10.18653/v1/2022.findings-naacl.184",
pages = "2402--2420",
abstract = "We propose a novel open-domain question-answering dataset based on the Common Crawl project. With a previously unseen number of around 130 million multilingual question-answer pairs (including about 60 million English data-points), we use our large-scale, natural, diverse and high-quality corpus to in-domain pre-train popular language models for the task of question-answering. In our experiments, we find that our Common Crawl Question Answering dataset (CCQA) achieves promising results in zero-shot, low resource and fine-tuned settings across multiple tasks, models and benchmarks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huber-etal-2022-ccqa">
<titleInfo>
<title>CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Huber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Armen</namePart>
<namePart type="family">Aghajanyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barlas</namePart>
<namePart type="family">Oguz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmytro</namePart>
<namePart type="family">Okhonko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonal</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xilun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a novel open-domain question-answering dataset based on the Common Crawl project. With a previously unseen number of around 130 million multilingual question-answer pairs (including about 60 million English data-points), we use our large-scale, natural, diverse and high-quality corpus to in-domain pre-train popular language models for the task of question-answering. In our experiments, we find that our Common Crawl Question Answering dataset (CCQA) achieves promising results in zero-shot, low resource and fine-tuned settings across multiple tasks, models and benchmarks.</abstract>
<identifier type="citekey">huber-etal-2022-ccqa</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.184</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.184</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>2402</start>
<end>2420</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training
%A Huber, Patrick
%A Aghajanyan, Armen
%A Oguz, Barlas
%A Okhonko, Dmytro
%A Yih, Scott
%A Gupta, Sonal
%A Chen, Xilun
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F huber-etal-2022-ccqa
%X We propose a novel open-domain question-answering dataset based on the Common Crawl project. With a previously unseen number of around 130 million multilingual question-answer pairs (including about 60 million English data-points), we use our large-scale, natural, diverse and high-quality corpus to in-domain pre-train popular language models for the task of question-answering. In our experiments, we find that our Common Crawl Question Answering dataset (CCQA) achieves promising results in zero-shot, low resource and fine-tuned settings across multiple tasks, models and benchmarks.
%R 10.18653/v1/2022.findings-naacl.184
%U https://aclanthology.org/2022.findings-naacl.184
%U https://doi.org/10.18653/v1/2022.findings-naacl.184
%P 2402-2420
Markdown (Informal)
[CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training](https://aclanthology.org/2022.findings-naacl.184) (Huber et al., Findings 2022)
ACL