@inproceedings{dhawan-etal-2026-improving,
title = "Improving Indigenous Language Machine Translation with Synthetic Data and Language-Specific Preprocessing",
author = "Dhawan, Aashish and
Driggers-Ellis, Christopher and
Grant, Christan and
Wang, Daisy Zhe",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Washington, Jonathan and
Oco, Nathaniel and
Zhao, Xiaobing",
booktitle = "Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages ({L}o{R}es{MT} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.loresmt-1.10/",
pages = "119--126",
ISBN = "979-8-89176-366-1",
abstract = "Machine translation for Indigenous and other low-resource languages is constrained by limited parallel data, orthographic variation, and evaluation instability for morphologically rich languages. In this work, we study Spanish{--}Aymara, Spanish{--}Guarani, and Spanish{--}Quechua translation in the context of the AmericasNLP benchmarks, focusing on data-centric improvements rather than architectural changes. We augment curated parallel corpora with forward-translated synthetic sentence pairs generated using a high-capacity multilingual translation model, while applying conservative, language-specific preprocessing tailored to each language. Training data is filtered using length-ratio constraints and deduplication, whereas official development sets are left unfiltered to ensure fair evaluation. We fine-tune a multilingual mBART model under curated-only and curated+synthetic settings and evaluate performance primarily using chrF++, which is better suited for agglutinative languages than BLEU. Across all three languages, synthetic data augmentation consistently improves chrF++, with the largest gains observed for Aymara and Guarani, while Quechua benefits primarily from deterministic orthographic normalization. Our analysis highlights both the effectiveness and the limitations of generic preprocessing for highly agglutinative languages, suggesting that data-centric augmentation and language-aware normalization are strong, reproducible baselines for low-resource Indigenous language machine translation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dhawan-etal-2026-improving">
<titleInfo>
<title>Improving Indigenous Language Machine Translation with Synthetic Data and Language-Specific Preprocessing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aashish</namePart>
<namePart type="family">Dhawan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Driggers-Ellis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christan</namePart>
<namePart type="family">Grant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisy</namePart>
<namePart type="given">Zhe</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages (LoResMT 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-366-1</identifier>
</relatedItem>
<abstract>Machine translation for Indigenous and other low-resource languages is constrained by limited parallel data, orthographic variation, and evaluation instability for morphologically rich languages. In this work, we study Spanish–Aymara, Spanish–Guarani, and Spanish–Quechua translation in the context of the AmericasNLP benchmarks, focusing on data-centric improvements rather than architectural changes. We augment curated parallel corpora with forward-translated synthetic sentence pairs generated using a high-capacity multilingual translation model, while applying conservative, language-specific preprocessing tailored to each language. Training data is filtered using length-ratio constraints and deduplication, whereas official development sets are left unfiltered to ensure fair evaluation. We fine-tune a multilingual mBART model under curated-only and curated+synthetic settings and evaluate performance primarily using chrF++, which is better suited for agglutinative languages than BLEU. Across all three languages, synthetic data augmentation consistently improves chrF++, with the largest gains observed for Aymara and Guarani, while Quechua benefits primarily from deterministic orthographic normalization. Our analysis highlights both the effectiveness and the limitations of generic preprocessing for highly agglutinative languages, suggesting that data-centric augmentation and language-aware normalization are strong, reproducible baselines for low-resource Indigenous language machine translation.</abstract>
<identifier type="citekey">dhawan-etal-2026-improving</identifier>
<location>
<url>https://aclanthology.org/2026.loresmt-1.10/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>119</start>
<end>126</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Indigenous Language Machine Translation with Synthetic Data and Language-Specific Preprocessing
%A Dhawan, Aashish
%A Driggers-Ellis, Christopher
%A Grant, Christan
%A Wang, Daisy Zhe
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Zhao, Xiaobing
%S Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages (LoResMT 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-366-1
%F dhawan-etal-2026-improving
%X Machine translation for Indigenous and other low-resource languages is constrained by limited parallel data, orthographic variation, and evaluation instability for morphologically rich languages. In this work, we study Spanish–Aymara, Spanish–Guarani, and Spanish–Quechua translation in the context of the AmericasNLP benchmarks, focusing on data-centric improvements rather than architectural changes. We augment curated parallel corpora with forward-translated synthetic sentence pairs generated using a high-capacity multilingual translation model, while applying conservative, language-specific preprocessing tailored to each language. Training data is filtered using length-ratio constraints and deduplication, whereas official development sets are left unfiltered to ensure fair evaluation. We fine-tune a multilingual mBART model under curated-only and curated+synthetic settings and evaluate performance primarily using chrF++, which is better suited for agglutinative languages than BLEU. Across all three languages, synthetic data augmentation consistently improves chrF++, with the largest gains observed for Aymara and Guarani, while Quechua benefits primarily from deterministic orthographic normalization. Our analysis highlights both the effectiveness and the limitations of generic preprocessing for highly agglutinative languages, suggesting that data-centric augmentation and language-aware normalization are strong, reproducible baselines for low-resource Indigenous language machine translation.
%U https://aclanthology.org/2026.loresmt-1.10/
%P 119-126
Markdown (Informal)
[Improving Indigenous Language Machine Translation with Synthetic Data and Language-Specific Preprocessing](https://aclanthology.org/2026.loresmt-1.10/) (Dhawan et al., LoResMT 2026)
ACL