TY - JOUR
T1 - Tydi qa
T2 - A benchmark for information-seeking question answering in typologically diverse languages
AU - Clark, Jonathan H.
AU - Choi, Eunsol
AU - Collins, Michael
AU - Garrette, Dan
AU - Kwiatkowski, Tom
AU - Nikolaev, Vitaly
AU - Palomaki, Jennimaria
N1 - Publisher Copyright:
© 2020 Association for Computational Linguistics.
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85094427355&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85094427355&partnerID=8YFLogxK
U2 - 10.1162/tacl_a_00317
DO - 10.1162/tacl_a_00317
M3 - Article
AN - SCOPUS:85094427355
SN - 2307-387X
VL - 8
SP - 454
EP - 470
JO - Transactions of the Association for Computational Linguistics
JF - Transactions of the Association for Computational Linguistics
ER -