@inproceedings{shurtz-etal-2025-scripts,
title = "When Scripts Diverge: Strengthening Low-Resource Neural Machine Translation Through Phonetic Cross-Lingual Transfer",
author = "Shurtz, Ammon and
Richardson, Christian and
Richardson, Stephen D.",
editor = "Adelani, David Ifeoluwa and
Arnett, Catherine and
Ataman, Duygu and
Chang, Tyler A. and
Gonen, Hila and
Raja, Rahul and
Schmidt, Fabian and
Stap, David and
Wang, Jiayi",
booktitle = "Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)",
month = nov,
year = "2025",
address = "Suzhuo, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.mrl-main.22/",
pages = "336--346",
ISBN = "979-8-89176-345-6",
abstract = "Multilingual Neural Machine Translation (MNMT) models enhance translation quality for low-resource languages by exploiting cross-lingual similarities during training{---}a process known as knowledge transfer. This transfer is particularly effective between languages that share lexical or structural features, often enabled by a common orthography. However, languages with strong phonetic and lexical similarities but distinct writing systems experience limited benefits, as the absence of a shared orthography hinders knowledge transfer. To address this limitation, we propose an approach based on phonetic information that enhances token-level alignment across scripts by leveraging transliterations. We systematically evaluate several phonetic transcription techniques and strategies for incorporating phonetic information into NMT models. Our results show that using a shared encoder to process orthographic and phonetic inputs separately consistently yields the best performance for Khmer, Thai, and Lao in both directions with English, and that our custom Cognate-Aware Transliteration (CAT) method consistently improves translation quality over the baseline."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shurtz-etal-2025-scripts">
<titleInfo>
<title>When Scripts Diverge: Strengthening Low-Resource Neural Machine Translation Through Phonetic Cross-Lingual Transfer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ammon</namePart>
<namePart type="family">Shurtz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Richardson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Richardson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duygu</namePart>
<namePart type="family">Ataman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hila</namePart>
<namePart type="family">Gonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Raja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Schmidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</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">Suzhuo, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-345-6</identifier>
</relatedItem>
<abstract>Multilingual Neural Machine Translation (MNMT) models enhance translation quality for low-resource languages by exploiting cross-lingual similarities during training—a process known as knowledge transfer. This transfer is particularly effective between languages that share lexical or structural features, often enabled by a common orthography. However, languages with strong phonetic and lexical similarities but distinct writing systems experience limited benefits, as the absence of a shared orthography hinders knowledge transfer. To address this limitation, we propose an approach based on phonetic information that enhances token-level alignment across scripts by leveraging transliterations. We systematically evaluate several phonetic transcription techniques and strategies for incorporating phonetic information into NMT models. Our results show that using a shared encoder to process orthographic and phonetic inputs separately consistently yields the best performance for Khmer, Thai, and Lao in both directions with English, and that our custom Cognate-Aware Transliteration (CAT) method consistently improves translation quality over the baseline.</abstract>
<identifier type="citekey">shurtz-etal-2025-scripts</identifier>
<location>
<url>https://aclanthology.org/2025.mrl-main.22/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>336</start>
<end>346</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Scripts Diverge: Strengthening Low-Resource Neural Machine Translation Through Phonetic Cross-Lingual Transfer
%A Shurtz, Ammon
%A Richardson, Christian
%A Richardson, Stephen D.
%Y Adelani, David Ifeoluwa
%Y Arnett, Catherine
%Y Ataman, Duygu
%Y Chang, Tyler A.
%Y Gonen, Hila
%Y Raja, Rahul
%Y Schmidt, Fabian
%Y Stap, David
%Y Wang, Jiayi
%S Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhuo, China
%@ 979-8-89176-345-6
%F shurtz-etal-2025-scripts
%X Multilingual Neural Machine Translation (MNMT) models enhance translation quality for low-resource languages by exploiting cross-lingual similarities during training—a process known as knowledge transfer. This transfer is particularly effective between languages that share lexical or structural features, often enabled by a common orthography. However, languages with strong phonetic and lexical similarities but distinct writing systems experience limited benefits, as the absence of a shared orthography hinders knowledge transfer. To address this limitation, we propose an approach based on phonetic information that enhances token-level alignment across scripts by leveraging transliterations. We systematically evaluate several phonetic transcription techniques and strategies for incorporating phonetic information into NMT models. Our results show that using a shared encoder to process orthographic and phonetic inputs separately consistently yields the best performance for Khmer, Thai, and Lao in both directions with English, and that our custom Cognate-Aware Transliteration (CAT) method consistently improves translation quality over the baseline.
%U https://aclanthology.org/2025.mrl-main.22/
%P 336-346
Markdown (Informal)
[When Scripts Diverge: Strengthening Low-Resource Neural Machine Translation Through Phonetic Cross-Lingual Transfer](https://aclanthology.org/2025.mrl-main.22/) (Shurtz et al., MRL 2025)
ACL