@inproceedings{jones-etal-2023-gatitos,
title = "{GATITOS}: Using a New Multilingual Lexicon for Low-resource Machine Translation",
author = "Jones, Alexander and
Caswell, Isaac and
Firat, Orhan and
Saxena, Ishank",
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.26",
doi = "10.18653/v1/2023.emnlp-main.26",
pages = "371--405",
abstract = "Modern machine translation models and language models are able to translate without having been trained on parallel data, greatly expanding the set of languages that they can serve. However, these models still struggle in a variety of predictable ways, a problem that cannot be overcome without at least some trusted bilingual data. This work expands on a cheap and abundant resource to combat this problem: bilingual lexica. We test the efficacy of bilingual lexica in a real-world set-up, on 200-language translation models trained on web-crawled text. We present several findings: (1) using lexical data augmentation, we demonstrate sizable performance gains for unsupervised translation; (2) we compare several families of data augmentation, demonstrating that they yield similar improvements, and can be combined for even greater improvements; (3) we demonstrate the importance of carefully curated lexica over larger, noisier ones, especially with larger models; and (4) we compare the efficacy of multilingual lexicon data versus human-translated parallel data. Based on results from (3), we develop and open-source GATITOS, a high-quality, curated dataset in 168 tail languages, one of the first human-translated resources to cover many of these languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jones-etal-2023-gatitos">
<titleInfo>
<title>GATITOS: Using a New Multilingual Lexicon for Low-resource Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Jones</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaac</namePart>
<namePart type="family">Caswell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orhan</namePart>
<namePart type="family">Firat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ishank</namePart>
<namePart type="family">Saxena</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>Modern machine translation models and language models are able to translate without having been trained on parallel data, greatly expanding the set of languages that they can serve. However, these models still struggle in a variety of predictable ways, a problem that cannot be overcome without at least some trusted bilingual data. This work expands on a cheap and abundant resource to combat this problem: bilingual lexica. We test the efficacy of bilingual lexica in a real-world set-up, on 200-language translation models trained on web-crawled text. We present several findings: (1) using lexical data augmentation, we demonstrate sizable performance gains for unsupervised translation; (2) we compare several families of data augmentation, demonstrating that they yield similar improvements, and can be combined for even greater improvements; (3) we demonstrate the importance of carefully curated lexica over larger, noisier ones, especially with larger models; and (4) we compare the efficacy of multilingual lexicon data versus human-translated parallel data. Based on results from (3), we develop and open-source GATITOS, a high-quality, curated dataset in 168 tail languages, one of the first human-translated resources to cover many of these languages.</abstract>
<identifier type="citekey">jones-etal-2023-gatitos</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.26</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.26</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>371</start>
<end>405</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GATITOS: Using a New Multilingual Lexicon for Low-resource Machine Translation
%A Jones, Alexander
%A Caswell, Isaac
%A Firat, Orhan
%A Saxena, Ishank
%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 jones-etal-2023-gatitos
%X Modern machine translation models and language models are able to translate without having been trained on parallel data, greatly expanding the set of languages that they can serve. However, these models still struggle in a variety of predictable ways, a problem that cannot be overcome without at least some trusted bilingual data. This work expands on a cheap and abundant resource to combat this problem: bilingual lexica. We test the efficacy of bilingual lexica in a real-world set-up, on 200-language translation models trained on web-crawled text. We present several findings: (1) using lexical data augmentation, we demonstrate sizable performance gains for unsupervised translation; (2) we compare several families of data augmentation, demonstrating that they yield similar improvements, and can be combined for even greater improvements; (3) we demonstrate the importance of carefully curated lexica over larger, noisier ones, especially with larger models; and (4) we compare the efficacy of multilingual lexicon data versus human-translated parallel data. Based on results from (3), we develop and open-source GATITOS, a high-quality, curated dataset in 168 tail languages, one of the first human-translated resources to cover many of these languages.
%R 10.18653/v1/2023.emnlp-main.26
%U https://aclanthology.org/2023.emnlp-main.26
%U https://doi.org/10.18653/v1/2023.emnlp-main.26
%P 371-405
Markdown (Informal)
[GATITOS: Using a New Multilingual Lexicon for Low-resource Machine Translation](https://aclanthology.org/2023.emnlp-main.26) (Jones et al., EMNLP 2023)
ACL