@article{clark-etal-2020-tydi,
title = "{T}y{D}i {QA}: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages",
author = "Clark, Jonathan H. and
Choi, Eunsol and
Collins, Michael and
Garrette, Dan and
Kwiatkowski, Tom and
Nikolaev, Vitaly and
Palomaki, Jennimaria",
editor = "Johnson, Mark and
Roark, Brian and
Nenkova, Ani",
journal = "Transactions of the Association for Computational Linguistics",
volume = "8",
year = "2020",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2020.tacl-1.30",
doi = "10.1162/tacl_a_00317",
pages = "454--470",
abstract = "Confidently making progress on multilingual modeling requires challenging, trustworthy evaluations. We present TyDi QA{---}a question answering dataset covering 11 typologically diverse languages with 204K question-answer pairs. The languages of TyDi QA are diverse with regard to their typology{---}the set of linguistic features each language expresses{---}such that we expect models performing well on this set to generalize across a large number of the world{'}s languages. We present a quantitative analysis of the data quality and example-level qualitative linguistic analyses of observed language phenomena that would not be found in English-only corpora. To provide a realistic information-seeking task and avoid priming effects, questions are written by people who want to know the answer, but don{'}t know the answer yet, and the data is collected directly in each language without the use of translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="clark-etal-2020-tydi">
<titleInfo>
<title>TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Collins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Garrette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kwiatkowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vitaly</namePart>
<namePart type="family">Nikolaev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennimaria</namePart>
<namePart type="family">Palomaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Confidently making progress on multilingual modeling requires challenging, trustworthy evaluations. We present TyDi QA—a question answering dataset covering 11 typologically diverse languages with 204K question-answer pairs. The languages of TyDi QA are diverse with regard to their typology—the set of linguistic features each language expresses—such that we expect models performing well on this set to generalize across a large number of the world’s languages. We present a quantitative analysis of the data quality and example-level qualitative linguistic analyses of observed language phenomena that would not be found in English-only corpora. To provide a realistic information-seeking task and avoid priming effects, questions are written by people who want to know the answer, but don’t know the answer yet, and the data is collected directly in each language without the use of translation.</abstract>
<identifier type="citekey">clark-etal-2020-tydi</identifier>
<identifier type="doi">10.1162/tacl_a_00317</identifier>
<location>
<url>https://aclanthology.org/2020.tacl-1.30</url>
</location>
<part>
<date>2020</date>
<detail type="volume"><number>8</number></detail>
<extent unit="page">
<start>454</start>
<end>470</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages
%A Clark, Jonathan H.
%A Choi, Eunsol
%A Collins, Michael
%A Garrette, Dan
%A Kwiatkowski, Tom
%A Nikolaev, Vitaly
%A Palomaki, Jennimaria
%J Transactions of the Association for Computational Linguistics
%D 2020
%V 8
%I MIT Press
%C Cambridge, MA
%F clark-etal-2020-tydi
%X Confidently making progress on multilingual modeling requires challenging, trustworthy evaluations. We present TyDi QA—a question answering dataset covering 11 typologically diverse languages with 204K question-answer pairs. The languages of TyDi QA are diverse with regard to their typology—the set of linguistic features each language expresses—such that we expect models performing well on this set to generalize across a large number of the world’s languages. We present a quantitative analysis of the data quality and example-level qualitative linguistic analyses of observed language phenomena that would not be found in English-only corpora. To provide a realistic information-seeking task and avoid priming effects, questions are written by people who want to know the answer, but don’t know the answer yet, and the data is collected directly in each language without the use of translation.
%R 10.1162/tacl_a_00317
%U https://aclanthology.org/2020.tacl-1.30
%U https://doi.org/10.1162/tacl_a_00317
%P 454-470
Markdown (Informal)
[TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages](https://aclanthology.org/2020.tacl-1.30) (Clark et al., TACL 2020)
ACL