@inproceedings{asai-etal-2022-mia,
title = "{MIA} 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages",
author = "Asai, Akari and
Longpre, Shayne and
Kasai, Jungo and
Lee, Chia-Hsuan and
Zhang, Rui and
Hu, Junjie and
Yamada, Ikuya and
Clark, Jonathan H. and
Choi, Eunsol",
editor = "Asai, Akari and
Choi, Eunsol and
Clark, Jonathan H. and
Hu, Junjie and
Lee, Chia-Hsuan and
Kasai, Jungo and
Longpre, Shayne and
Yamada, Ikuya and
Zhang, Rui",
booktitle = "Proceedings of the Workshop on Multilingual Information Access (MIA)",
month = jul,
year = "2022",
address = "Seattle, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.mia-1.11",
doi = "10.18653/v1/2022.mia-1.11",
pages = "108--120",
abstract = "We present the results of the Workshop on Multilingual Information Access (MIA) 2022 Shared Task, evaluating cross-lingual open-retrieval question answering (QA) systems in 16 typologically diverse languages. In this task, we adapted two large-scale cross-lingual open-retrieval QA datasets in 14 typologically diverse languages, and newly annotated open-retrieval QA data in 2 underrepresented languages: Tagalog and Tamil. Four teams submitted their systems. The best constrained system uses entity-aware contextualized representations for document retrieval, thereby achieving an average F1 score of 31.6, which is 4.1 F1 absolute higher than the challenging baseline. The best system obtains particularly significant improvements in Tamil (20.8 F1), whereas most of the other systems yield nearly zero scores. The best unconstrained system achieves 32.2 F1, outperforming our baseline by 4.5 points.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="asai-etal-2022-mia">
<titleInfo>
<title>MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akari</namePart>
<namePart type="family">Asai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shayne</namePart>
<namePart type="family">Longpre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungo</namePart>
<namePart type="family">Kasai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Hsuan</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junjie</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ikuya</namePart>
<namePart type="family">Yamada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Multilingual Information Access (MIA)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akari</namePart>
<namePart type="family">Asai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junjie</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Hsuan</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungo</namePart>
<namePart type="family">Kasai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shayne</namePart>
<namePart type="family">Longpre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ikuya</namePart>
<namePart type="family">Yamada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present the results of the Workshop on Multilingual Information Access (MIA) 2022 Shared Task, evaluating cross-lingual open-retrieval question answering (QA) systems in 16 typologically diverse languages. In this task, we adapted two large-scale cross-lingual open-retrieval QA datasets in 14 typologically diverse languages, and newly annotated open-retrieval QA data in 2 underrepresented languages: Tagalog and Tamil. Four teams submitted their systems. The best constrained system uses entity-aware contextualized representations for document retrieval, thereby achieving an average F1 score of 31.6, which is 4.1 F1 absolute higher than the challenging baseline. The best system obtains particularly significant improvements in Tamil (20.8 F1), whereas most of the other systems yield nearly zero scores. The best unconstrained system achieves 32.2 F1, outperforming our baseline by 4.5 points.</abstract>
<identifier type="citekey">asai-etal-2022-mia</identifier>
<identifier type="doi">10.18653/v1/2022.mia-1.11</identifier>
<location>
<url>https://aclanthology.org/2022.mia-1.11</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>108</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages
%A Asai, Akari
%A Longpre, Shayne
%A Kasai, Jungo
%A Lee, Chia-Hsuan
%A Zhang, Rui
%A Hu, Junjie
%A Yamada, Ikuya
%A Clark, Jonathan H.
%A Choi, Eunsol
%Y Asai, Akari
%Y Choi, Eunsol
%Y Clark, Jonathan H.
%Y Hu, Junjie
%Y Lee, Chia-Hsuan
%Y Kasai, Jungo
%Y Longpre, Shayne
%Y Yamada, Ikuya
%Y Zhang, Rui
%S Proceedings of the Workshop on Multilingual Information Access (MIA)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, USA
%F asai-etal-2022-mia
%X We present the results of the Workshop on Multilingual Information Access (MIA) 2022 Shared Task, evaluating cross-lingual open-retrieval question answering (QA) systems in 16 typologically diverse languages. In this task, we adapted two large-scale cross-lingual open-retrieval QA datasets in 14 typologically diverse languages, and newly annotated open-retrieval QA data in 2 underrepresented languages: Tagalog and Tamil. Four teams submitted their systems. The best constrained system uses entity-aware contextualized representations for document retrieval, thereby achieving an average F1 score of 31.6, which is 4.1 F1 absolute higher than the challenging baseline. The best system obtains particularly significant improvements in Tamil (20.8 F1), whereas most of the other systems yield nearly zero scores. The best unconstrained system achieves 32.2 F1, outperforming our baseline by 4.5 points.
%R 10.18653/v1/2022.mia-1.11
%U https://aclanthology.org/2022.mia-1.11
%U https://doi.org/10.18653/v1/2022.mia-1.11
%P 108-120
Markdown (Informal)
[MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages](https://aclanthology.org/2022.mia-1.11) (Asai et al., MIA 2022)
ACL
- Akari Asai, Shayne Longpre, Jungo Kasai, Chia-Hsuan Lee, Rui Zhang, Junjie Hu, Ikuya Yamada, Jonathan H. Clark, and Eunsol Choi. 2022. MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages. In Proceedings of the Workshop on Multilingual Information Access (MIA), pages 108–120, Seattle, USA. Association for Computational Linguistics.