@inproceedings{abujabal-etal-2019-comqa,
title = "{C}om{QA}: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters",
author = "Abujabal, Abdalghani and
Saha Roy, Rishiraj and
Yahya, Mohamed and
Weikum, Gerhard",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1027",
doi = "10.18653/v1/N19-1027",
pages = "307--317",
abstract = "To bridge the gap between the capabilities of the state-of-the-art in factoid question answering (QA) and what users ask, we need large datasets of real user questions that capture the various question phenomena users are interested in, and the diverse ways in which these questions are formulated. We introduce ComQA, a large dataset of real user questions that exhibit different challenging aspects such as compositionality, temporal reasoning, and comparisons. ComQA questions come from the WikiAnswers community QA platform, which typically contains questions that are not satisfactorily answerable by existing search engine technology. Through a large crowdsourcing effort, we clean the question dataset, group questions into paraphrase clusters, and annotate clusters with their answers. ComQA contains 11,214 questions grouped into 4,834 paraphrase clusters. We detail the process of constructing ComQA, including the measures taken to ensure its high quality while making effective use of crowdsourcing. We also present an extensive analysis of the dataset and the results achieved by state-of-the-art systems on ComQA, demonstrating that our dataset can be a driver of future research on QA.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abujabal-etal-2019-comqa">
<titleInfo>
<title>ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdalghani</namePart>
<namePart type="family">Abujabal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishiraj</namePart>
<namePart type="family">Saha Roy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Yahya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerhard</namePart>
<namePart type="family">Weikum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To bridge the gap between the capabilities of the state-of-the-art in factoid question answering (QA) and what users ask, we need large datasets of real user questions that capture the various question phenomena users are interested in, and the diverse ways in which these questions are formulated. We introduce ComQA, a large dataset of real user questions that exhibit different challenging aspects such as compositionality, temporal reasoning, and comparisons. ComQA questions come from the WikiAnswers community QA platform, which typically contains questions that are not satisfactorily answerable by existing search engine technology. Through a large crowdsourcing effort, we clean the question dataset, group questions into paraphrase clusters, and annotate clusters with their answers. ComQA contains 11,214 questions grouped into 4,834 paraphrase clusters. We detail the process of constructing ComQA, including the measures taken to ensure its high quality while making effective use of crowdsourcing. We also present an extensive analysis of the dataset and the results achieved by state-of-the-art systems on ComQA, demonstrating that our dataset can be a driver of future research on QA.</abstract>
<identifier type="citekey">abujabal-etal-2019-comqa</identifier>
<identifier type="doi">10.18653/v1/N19-1027</identifier>
<location>
<url>https://aclanthology.org/N19-1027</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>307</start>
<end>317</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters
%A Abujabal, Abdalghani
%A Saha Roy, Rishiraj
%A Yahya, Mohamed
%A Weikum, Gerhard
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F abujabal-etal-2019-comqa
%X To bridge the gap between the capabilities of the state-of-the-art in factoid question answering (QA) and what users ask, we need large datasets of real user questions that capture the various question phenomena users are interested in, and the diverse ways in which these questions are formulated. We introduce ComQA, a large dataset of real user questions that exhibit different challenging aspects such as compositionality, temporal reasoning, and comparisons. ComQA questions come from the WikiAnswers community QA platform, which typically contains questions that are not satisfactorily answerable by existing search engine technology. Through a large crowdsourcing effort, we clean the question dataset, group questions into paraphrase clusters, and annotate clusters with their answers. ComQA contains 11,214 questions grouped into 4,834 paraphrase clusters. We detail the process of constructing ComQA, including the measures taken to ensure its high quality while making effective use of crowdsourcing. We also present an extensive analysis of the dataset and the results achieved by state-of-the-art systems on ComQA, demonstrating that our dataset can be a driver of future research on QA.
%R 10.18653/v1/N19-1027
%U https://aclanthology.org/N19-1027
%U https://doi.org/10.18653/v1/N19-1027
%P 307-317
Markdown (Informal)
[ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters](https://aclanthology.org/N19-1027) (Abujabal et al., NAACL 2019)
ACL