@inproceedings{castelli-etal-2020-techqa,
title = "The {T}ech{QA} Dataset",
author = "Castelli, Vittorio and
Chakravarti, Rishav and
Dana, Saswati and
Ferritto, Anthony and
Florian, Radu and
Franz, Martin and
Garg, Dinesh and
Khandelwal, Dinesh and
McCarley, Scott and
McCawley, Michael and
Nasr, Mohamed and
Pan, Lin and
Pendus, Cezar and
Pitrelli, John and
Pujar, Saurabh and
Roukos, Salim and
Sakrajda, Andrzej and
Sil, Avi and
Uceda-Sosa, Rosario and
Ward, Todd and
Zhang, Rong",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.117",
doi = "10.18653/v1/2020.acl-main.117",
pages = "1269--1278",
abstract = "We introduce TECHQA, a domain-adaptation question answering dataset for the technical support domain. The TECHQA corpus highlights two real-world issues from the automated customer support domain. First, it contains actual questions posed by users on a technical forum, rather than questions generated specifically for a competition or a task. Second, it has a real-world size {--} 600 training, 310 dev, and 490 evaluation question/answer pairs {--} thus reflecting the cost of creating large labeled datasets with actual data. Hence, TECHQA is meant to stimulate research in domain adaptation rather than as a resource to build QA systems from scratch. TECHQA was obtained by crawling the IBMDeveloper and DeveloperWorks forums for questions with accepted answers provided in an IBM Technote{---}a technical document that addresses a specific technical issue. We also release a collection of the 801,998 Technotes available on the web as of April 4, 2019 as a companion resource that can be used to learn representations of the IT domain language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="castelli-etal-2020-techqa">
<titleInfo>
<title>The TechQA Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vittorio</namePart>
<namePart type="family">Castelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishav</namePart>
<namePart type="family">Chakravarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saswati</namePart>
<namePart type="family">Dana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="family">Ferritto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radu</namePart>
<namePart type="family">Florian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Franz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dinesh</namePart>
<namePart type="family">Garg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dinesh</namePart>
<namePart type="family">Khandelwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">McCarley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">McCawley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Nasr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cezar</namePart>
<namePart type="family">Pendus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Pitrelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saurabh</namePart>
<namePart type="family">Pujar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salim</namePart>
<namePart type="family">Roukos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrzej</namePart>
<namePart type="family">Sakrajda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avi</namePart>
<namePart type="family">Sil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rosario</namePart>
<namePart type="family">Uceda-Sosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Todd</namePart>
<namePart type="family">Ward</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce TECHQA, a domain-adaptation question answering dataset for the technical support domain. The TECHQA corpus highlights two real-world issues from the automated customer support domain. First, it contains actual questions posed by users on a technical forum, rather than questions generated specifically for a competition or a task. Second, it has a real-world size – 600 training, 310 dev, and 490 evaluation question/answer pairs – thus reflecting the cost of creating large labeled datasets with actual data. Hence, TECHQA is meant to stimulate research in domain adaptation rather than as a resource to build QA systems from scratch. TECHQA was obtained by crawling the IBMDeveloper and DeveloperWorks forums for questions with accepted answers provided in an IBM Technote—a technical document that addresses a specific technical issue. We also release a collection of the 801,998 Technotes available on the web as of April 4, 2019 as a companion resource that can be used to learn representations of the IT domain language.</abstract>
<identifier type="citekey">castelli-etal-2020-techqa</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.117</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.117</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>1269</start>
<end>1278</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The TechQA Dataset
%A Castelli, Vittorio
%A Chakravarti, Rishav
%A Dana, Saswati
%A Ferritto, Anthony
%A Florian, Radu
%A Franz, Martin
%A Garg, Dinesh
%A Khandelwal, Dinesh
%A McCarley, Scott
%A McCawley, Michael
%A Nasr, Mohamed
%A Pan, Lin
%A Pendus, Cezar
%A Pitrelli, John
%A Pujar, Saurabh
%A Roukos, Salim
%A Sakrajda, Andrzej
%A Sil, Avi
%A Uceda-Sosa, Rosario
%A Ward, Todd
%A Zhang, Rong
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F castelli-etal-2020-techqa
%X We introduce TECHQA, a domain-adaptation question answering dataset for the technical support domain. The TECHQA corpus highlights two real-world issues from the automated customer support domain. First, it contains actual questions posed by users on a technical forum, rather than questions generated specifically for a competition or a task. Second, it has a real-world size – 600 training, 310 dev, and 490 evaluation question/answer pairs – thus reflecting the cost of creating large labeled datasets with actual data. Hence, TECHQA is meant to stimulate research in domain adaptation rather than as a resource to build QA systems from scratch. TECHQA was obtained by crawling the IBMDeveloper and DeveloperWorks forums for questions with accepted answers provided in an IBM Technote—a technical document that addresses a specific technical issue. We also release a collection of the 801,998 Technotes available on the web as of April 4, 2019 as a companion resource that can be used to learn representations of the IT domain language.
%R 10.18653/v1/2020.acl-main.117
%U https://aclanthology.org/2020.acl-main.117
%U https://doi.org/10.18653/v1/2020.acl-main.117
%P 1269-1278
Markdown (Informal)
[The TechQA Dataset](https://aclanthology.org/2020.acl-main.117) (Castelli et al., ACL 2020)
ACL
- Vittorio Castelli, Rishav Chakravarti, Saswati Dana, Anthony Ferritto, Radu Florian, Martin Franz, Dinesh Garg, Dinesh Khandelwal, Scott McCarley, Michael McCawley, Mohamed Nasr, Lin Pan, Cezar Pendus, John Pitrelli, Saurabh Pujar, Salim Roukos, Andrzej Sakrajda, Avi Sil, Rosario Uceda-Sosa, et al.. 2020. The TechQA Dataset. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1269–1278, Online. Association for Computational Linguistics.