@inproceedings{gaim-etal-2023-question,
title = "Question-Answering in a Low-resourced Language: Benchmark Dataset and Models for {T}igrinya",
author = "Gaim, Fitsum and
Yang, Wonsuk and
Park, Hancheol and
Park, Jong",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.661/",
doi = "10.18653/v1/2023.acl-long.661",
pages = "11857--11870",
abstract = "Question-Answering (QA) has seen significant advances recently, achieving near human-level performance over some benchmarks. However, these advances focus on high-resourced languages such as English, while the task remains unexplored for most other languages, mainly due to the lack of annotated datasets. This work presents a native QA dataset for an East African language, Tigrinya. The dataset contains 10.6K question-answer pairs spanning 572 paragraphs extracted from 290 news articles on various topics. The dataset construction method is discussed, which is applicable to constructing similar resources for related languages. We present comprehensive experiments and analyses of several resource-efficient approaches to QA, including monolingual, cross-lingual, and multilingual setups, along with comparisons against machine-translated silver data. Our strong baseline models reach 76{\%} in the F1 score, while the estimated human performance is 92{\%}, indicating that the benchmark presents a good challenge for future work. We make the dataset, models, and leaderboard publicly available."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaim-etal-2023-question">
<titleInfo>
<title>Question-Answering in a Low-resourced Language: Benchmark Dataset and Models for Tigrinya</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fitsum</namePart>
<namePart type="family">Gaim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wonsuk</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hancheol</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jong</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Question-Answering (QA) has seen significant advances recently, achieving near human-level performance over some benchmarks. However, these advances focus on high-resourced languages such as English, while the task remains unexplored for most other languages, mainly due to the lack of annotated datasets. This work presents a native QA dataset for an East African language, Tigrinya. The dataset contains 10.6K question-answer pairs spanning 572 paragraphs extracted from 290 news articles on various topics. The dataset construction method is discussed, which is applicable to constructing similar resources for related languages. We present comprehensive experiments and analyses of several resource-efficient approaches to QA, including monolingual, cross-lingual, and multilingual setups, along with comparisons against machine-translated silver data. Our strong baseline models reach 76% in the F1 score, while the estimated human performance is 92%, indicating that the benchmark presents a good challenge for future work. We make the dataset, models, and leaderboard publicly available.</abstract>
<identifier type="citekey">gaim-etal-2023-question</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.661</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.661/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>11857</start>
<end>11870</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Question-Answering in a Low-resourced Language: Benchmark Dataset and Models for Tigrinya
%A Gaim, Fitsum
%A Yang, Wonsuk
%A Park, Hancheol
%A Park, Jong
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F gaim-etal-2023-question
%X Question-Answering (QA) has seen significant advances recently, achieving near human-level performance over some benchmarks. However, these advances focus on high-resourced languages such as English, while the task remains unexplored for most other languages, mainly due to the lack of annotated datasets. This work presents a native QA dataset for an East African language, Tigrinya. The dataset contains 10.6K question-answer pairs spanning 572 paragraphs extracted from 290 news articles on various topics. The dataset construction method is discussed, which is applicable to constructing similar resources for related languages. We present comprehensive experiments and analyses of several resource-efficient approaches to QA, including monolingual, cross-lingual, and multilingual setups, along with comparisons against machine-translated silver data. Our strong baseline models reach 76% in the F1 score, while the estimated human performance is 92%, indicating that the benchmark presents a good challenge for future work. We make the dataset, models, and leaderboard publicly available.
%R 10.18653/v1/2023.acl-long.661
%U https://aclanthology.org/2023.acl-long.661/
%U https://doi.org/10.18653/v1/2023.acl-long.661
%P 11857-11870
Markdown (Informal)
[Question-Answering in a Low-resourced Language: Benchmark Dataset and Models for Tigrinya](https://aclanthology.org/2023.acl-long.661/) (Gaim et al., ACL 2023)
ACL