@inproceedings{tran-etal-2025-exploiting,
title = "Exploiting Word Sense Disambiguation in Large Language Models for Machine Translation",
author = "Tran, Van-Hien and
Dabre, Raj and
Kaing, Hour and
Song, Haiyue and
Tanaka, Hideki and
Utiyama, Masao",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the First Workshop on Language Models for Low-Resource Languages",
month = jan,
year = "2025",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.loreslm-1.10/",
pages = "135--144",
abstract = "Machine Translation (MT) has made great strides with the use of Large Language Models (LLMs) and advanced prompting techniques. However, translating sentences with ambiguous words remains challenging, especially when LLMs have limited proficiency in the source language. This paper introduces two methods to enhance MT performance by leveraging the word sense disambiguation capabilities of LLMs. The first method integrates all the available senses of an ambiguous word into the prompting template. The second method uses a pre-trained source language model to predict the correct sense of the ambiguous word, which is then incorporated into the prompting template. Additionally, we propose two prompting template styles for providing word sense information to LLMs. Experiments on the HOLLY dataset demonstrate the effectiveness of our approach in improving MT performance."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-etal-2025-exploiting">
<titleInfo>
<title>Exploiting Word Sense Disambiguation in Large Language Models for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Van-Hien</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hour</namePart>
<namePart type="family">Kaing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyue</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Tanaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Language Models for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine Translation (MT) has made great strides with the use of Large Language Models (LLMs) and advanced prompting techniques. However, translating sentences with ambiguous words remains challenging, especially when LLMs have limited proficiency in the source language. This paper introduces two methods to enhance MT performance by leveraging the word sense disambiguation capabilities of LLMs. The first method integrates all the available senses of an ambiguous word into the prompting template. The second method uses a pre-trained source language model to predict the correct sense of the ambiguous word, which is then incorporated into the prompting template. Additionally, we propose two prompting template styles for providing word sense information to LLMs. Experiments on the HOLLY dataset demonstrate the effectiveness of our approach in improving MT performance.</abstract>
<identifier type="citekey">tran-etal-2025-exploiting</identifier>
<location>
<url>https://aclanthology.org/2025.loreslm-1.10/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>135</start>
<end>144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting Word Sense Disambiguation in Large Language Models for Machine Translation
%A Tran, Van-Hien
%A Dabre, Raj
%A Kaing, Hour
%A Song, Haiyue
%A Tanaka, Hideki
%A Utiyama, Masao
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the First Workshop on Language Models for Low-Resource Languages
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F tran-etal-2025-exploiting
%X Machine Translation (MT) has made great strides with the use of Large Language Models (LLMs) and advanced prompting techniques. However, translating sentences with ambiguous words remains challenging, especially when LLMs have limited proficiency in the source language. This paper introduces two methods to enhance MT performance by leveraging the word sense disambiguation capabilities of LLMs. The first method integrates all the available senses of an ambiguous word into the prompting template. The second method uses a pre-trained source language model to predict the correct sense of the ambiguous word, which is then incorporated into the prompting template. Additionally, we propose two prompting template styles for providing word sense information to LLMs. Experiments on the HOLLY dataset demonstrate the effectiveness of our approach in improving MT performance.
%U https://aclanthology.org/2025.loreslm-1.10/
%P 135-144
Markdown (Informal)
[Exploiting Word Sense Disambiguation in Large Language Models for Machine Translation](https://aclanthology.org/2025.loreslm-1.10/) (Tran et al., LoResLM 2025)
ACL