@inproceedings{nielsen-etal-2025-alligators,
title = "Alligators All Around: Mitigating Lexical Confusion in Low-resource Machine Translation",
author = "Nielsen, Elizabeth and
Caswell, Isaac Rayburn and
Luo, Jiaming and
Cherry, Colin",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-short.18/",
doi = "10.18653/v1/2025.naacl-short.18",
pages = "206--221",
ISBN = "979-8-89176-190-2",
abstract = "Current machine translation (MT) systems for low-resource languages have a particular failure mode: When translating words in a given domain, they tend to confuse words within that domain. So, for example, ``lion'' might be translated as ``alligator'', and ``orange'' might be rendered as ``purple.'' We propose a recall-based metric for measuring this problem and show that the problem exists in 122 low-resource languages. We then show that this problem can be mitigated by using a large language model (LLM) to post-edit the MT output, specifically by including the entire GATITOS lexicon for the relevant language as a very long context prompt. We show gains in average ChrF score over the set of 122 languages, and we show that the recall score for relevant lexical items also improves. Finally, we demonstrate that a small dedicated MT system with a general-purpose LLM as a post-editor is outperforms a lexicon-based RAG-LLM translator, suggesting a new paradigm for LLM use."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nielsen-etal-2025-alligators">
<titleInfo>
<title>Alligators All Around: Mitigating Lexical Confusion in Low-resource Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Nielsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaac</namePart>
<namePart type="given">Rayburn</namePart>
<namePart type="family">Caswell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaming</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-190-2</identifier>
</relatedItem>
<abstract>Current machine translation (MT) systems for low-resource languages have a particular failure mode: When translating words in a given domain, they tend to confuse words within that domain. So, for example, “lion” might be translated as “alligator”, and “orange” might be rendered as “purple.” We propose a recall-based metric for measuring this problem and show that the problem exists in 122 low-resource languages. We then show that this problem can be mitigated by using a large language model (LLM) to post-edit the MT output, specifically by including the entire GATITOS lexicon for the relevant language as a very long context prompt. We show gains in average ChrF score over the set of 122 languages, and we show that the recall score for relevant lexical items also improves. Finally, we demonstrate that a small dedicated MT system with a general-purpose LLM as a post-editor is outperforms a lexicon-based RAG-LLM translator, suggesting a new paradigm for LLM use.</abstract>
<identifier type="citekey">nielsen-etal-2025-alligators</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-short.18</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-short.18/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>206</start>
<end>221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Alligators All Around: Mitigating Lexical Confusion in Low-resource Machine Translation
%A Nielsen, Elizabeth
%A Caswell, Isaac Rayburn
%A Luo, Jiaming
%A Cherry, Colin
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-190-2
%F nielsen-etal-2025-alligators
%X Current machine translation (MT) systems for low-resource languages have a particular failure mode: When translating words in a given domain, they tend to confuse words within that domain. So, for example, “lion” might be translated as “alligator”, and “orange” might be rendered as “purple.” We propose a recall-based metric for measuring this problem and show that the problem exists in 122 low-resource languages. We then show that this problem can be mitigated by using a large language model (LLM) to post-edit the MT output, specifically by including the entire GATITOS lexicon for the relevant language as a very long context prompt. We show gains in average ChrF score over the set of 122 languages, and we show that the recall score for relevant lexical items also improves. Finally, we demonstrate that a small dedicated MT system with a general-purpose LLM as a post-editor is outperforms a lexicon-based RAG-LLM translator, suggesting a new paradigm for LLM use.
%R 10.18653/v1/2025.naacl-short.18
%U https://aclanthology.org/2025.naacl-short.18/
%U https://doi.org/10.18653/v1/2025.naacl-short.18
%P 206-221
Markdown (Informal)
[Alligators All Around: Mitigating Lexical Confusion in Low-resource Machine Translation](https://aclanthology.org/2025.naacl-short.18/) (Nielsen et al., NAACL 2025)
ACL