@inproceedings{agarwal-etal-2023-limit,
title = "{LIMIT}: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages",
author = "Agarwal, Milind and
Alam, Md Mahfuz Ibn and
Anastasopoulos, Antonios",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.895",
doi = "10.18653/v1/2023.emnlp-main.895",
pages = "14496--14519",
abstract = "Knowing the language of an input text/audio is a necessary first step for using almost every NLP tool such as taggers, parsers, or translation systems. Language identification is a well-studied problem, sometimes even considered solved; in reality, due to lack of data and computational challenges, current systems cannot accurately identify most of the world{'}s 7000 languages. To tackle this bottleneck, we first compile a corpus, MCS-350, of 50K multilingual and parallel children{'}s stories in 350+ languages. MCS-350 can serve as a benchmark for language identification of short texts and for 1400+ new translation directions in low-resource Indian and African languages. Second, we propose a novel misprediction-resolution hierarchical model, LIMIT, for language identification that reduces error by 55{\%} (from 0.71 to 0.32) on our compiled children{'}s stories dataset and by 40{\%} (from 0.23 to 0.14) on the FLORES-200 benchmark. Our method can expand language identification coverage into low-resource languages by relying solely on systemic misprediction patterns, bypassing the need to retrain large models from scratch.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agarwal-etal-2023-limit">
<titleInfo>
<title>LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Milind</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Mahfuz</namePart>
<namePart type="given">Ibn</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowing the language of an input text/audio is a necessary first step for using almost every NLP tool such as taggers, parsers, or translation systems. Language identification is a well-studied problem, sometimes even considered solved; in reality, due to lack of data and computational challenges, current systems cannot accurately identify most of the world’s 7000 languages. To tackle this bottleneck, we first compile a corpus, MCS-350, of 50K multilingual and parallel children’s stories in 350+ languages. MCS-350 can serve as a benchmark for language identification of short texts and for 1400+ new translation directions in low-resource Indian and African languages. Second, we propose a novel misprediction-resolution hierarchical model, LIMIT, for language identification that reduces error by 55% (from 0.71 to 0.32) on our compiled children’s stories dataset and by 40% (from 0.23 to 0.14) on the FLORES-200 benchmark. Our method can expand language identification coverage into low-resource languages by relying solely on systemic misprediction patterns, bypassing the need to retrain large models from scratch.</abstract>
<identifier type="citekey">agarwal-etal-2023-limit</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.895</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.895</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>14496</start>
<end>14519</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages
%A Agarwal, Milind
%A Alam, Md Mahfuz Ibn
%A Anastasopoulos, Antonios
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F agarwal-etal-2023-limit
%X Knowing the language of an input text/audio is a necessary first step for using almost every NLP tool such as taggers, parsers, or translation systems. Language identification is a well-studied problem, sometimes even considered solved; in reality, due to lack of data and computational challenges, current systems cannot accurately identify most of the world’s 7000 languages. To tackle this bottleneck, we first compile a corpus, MCS-350, of 50K multilingual and parallel children’s stories in 350+ languages. MCS-350 can serve as a benchmark for language identification of short texts and for 1400+ new translation directions in low-resource Indian and African languages. Second, we propose a novel misprediction-resolution hierarchical model, LIMIT, for language identification that reduces error by 55% (from 0.71 to 0.32) on our compiled children’s stories dataset and by 40% (from 0.23 to 0.14) on the FLORES-200 benchmark. Our method can expand language identification coverage into low-resource languages by relying solely on systemic misprediction patterns, bypassing the need to retrain large models from scratch.
%R 10.18653/v1/2023.emnlp-main.895
%U https://aclanthology.org/2023.emnlp-main.895
%U https://doi.org/10.18653/v1/2023.emnlp-main.895
%P 14496-14519
Markdown (Informal)
[LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages](https://aclanthology.org/2023.emnlp-main.895) (Agarwal et al., EMNLP 2023)
ACL