@inproceedings{pulipaka-barak-2026-translation,
title = "Can Translation Bridge the Data Gap for Low-Resource Languages? A Case Study of {H}indi and {T}elugu",
author = "Pulipaka, Venkata Naga Sai Vishnu Rohit and
Barak, Libby",
editor = "Choshen, Leshem and
Cotterell, Ryan and
Gul, Mustafa Omer and
Jumelet, Jaap and
Linzen, Tal and
Mueller, Aaron and
Salhan, Suchir and
Shah, Raj Sanjay and
Warstadt, Alex and
Wilcox, Ethan Gotlieb",
booktitle = "Proceedings of the Second {B}aby{LM} Workshop",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.babylm-main.22/",
pages = "279--288",
ISBN = "979-8-89176-475-0",
abstract = "Low-resource languages often lack sufficient training data for developing small language models, limiting the application of recent language acquisition benchmarks beyond English. Moreover, cross-language comparison is made harder given differences in training data composition and quality. We investigate whether machine translation can be used to create BabyLM-scale training corpora for low-resource languages by translating the English BabyLM corpus into Hindi and Telugu using IndicTrans2. We train GPT-BERT and GPT-Wee models and evaluate them using perplexity and linguistic benchmarks. GPT-BERT consistently outperforms GPT-Wee across both monolingual and bilingual settings. Although perplexity is lower on in-domain test data, this pattern is consistent across English and the translated languages, suggesting that the effect reflects domain similarity rather than artifacts introduced by translation. Furthermore, the models achieve competitive performance on linguistic evaluations relative to pretrained language models. These findings suggest that translation warrants further analysis to obtain data for developing and evaluating small language models in low-resource settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pulipaka-barak-2026-translation">
<titleInfo>
<title>Can Translation Bridge the Data Gap for Low-Resource Languages? A Case Study of Hindi and Telugu</title>
</titleInfo>
<name type="personal">
<namePart type="given">Venkata</namePart>
<namePart type="given">Naga</namePart>
<namePart type="given">Sai</namePart>
<namePart type="given">Vishnu</namePart>
<namePart type="given">Rohit</namePart>
<namePart type="family">Pulipaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Libby</namePart>
<namePart type="family">Barak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second BabyLM Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="given">Omer</namePart>
<namePart type="family">Gul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Jumelet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suchir</namePart>
<namePart type="family">Salhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="given">Sanjay</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Warstadt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="given">Gotlieb</namePart>
<namePart type="family">Wilcox</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-475-0</identifier>
</relatedItem>
<abstract>Low-resource languages often lack sufficient training data for developing small language models, limiting the application of recent language acquisition benchmarks beyond English. Moreover, cross-language comparison is made harder given differences in training data composition and quality. We investigate whether machine translation can be used to create BabyLM-scale training corpora for low-resource languages by translating the English BabyLM corpus into Hindi and Telugu using IndicTrans2. We train GPT-BERT and GPT-Wee models and evaluate them using perplexity and linguistic benchmarks. GPT-BERT consistently outperforms GPT-Wee across both monolingual and bilingual settings. Although perplexity is lower on in-domain test data, this pattern is consistent across English and the translated languages, suggesting that the effect reflects domain similarity rather than artifacts introduced by translation. Furthermore, the models achieve competitive performance on linguistic evaluations relative to pretrained language models. These findings suggest that translation warrants further analysis to obtain data for developing and evaluating small language models in low-resource settings.</abstract>
<identifier type="citekey">pulipaka-barak-2026-translation</identifier>
<location>
<url>https://aclanthology.org/2026.babylm-main.22/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>279</start>
<end>288</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Translation Bridge the Data Gap for Low-Resource Languages? A Case Study of Hindi and Telugu
%A Pulipaka, Venkata Naga Sai Vishnu Rohit
%A Barak, Libby
%Y Choshen, Leshem
%Y Cotterell, Ryan
%Y Gul, Mustafa Omer
%Y Jumelet, Jaap
%Y Linzen, Tal
%Y Mueller, Aaron
%Y Salhan, Suchir
%Y Shah, Raj Sanjay
%Y Warstadt, Alex
%Y Wilcox, Ethan Gotlieb
%S Proceedings of the Second BabyLM Workshop
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-475-0
%F pulipaka-barak-2026-translation
%X Low-resource languages often lack sufficient training data for developing small language models, limiting the application of recent language acquisition benchmarks beyond English. Moreover, cross-language comparison is made harder given differences in training data composition and quality. We investigate whether machine translation can be used to create BabyLM-scale training corpora for low-resource languages by translating the English BabyLM corpus into Hindi and Telugu using IndicTrans2. We train GPT-BERT and GPT-Wee models and evaluate them using perplexity and linguistic benchmarks. GPT-BERT consistently outperforms GPT-Wee across both monolingual and bilingual settings. Although perplexity is lower on in-domain test data, this pattern is consistent across English and the translated languages, suggesting that the effect reflects domain similarity rather than artifacts introduced by translation. Furthermore, the models achieve competitive performance on linguistic evaluations relative to pretrained language models. These findings suggest that translation warrants further analysis to obtain data for developing and evaluating small language models in low-resource settings.
%U https://aclanthology.org/2026.babylm-main.22/
%P 279-288
Markdown (Informal)
[Can Translation Bridge the Data Gap for Low-Resource Languages? A Case Study of Hindi and Telugu](https://aclanthology.org/2026.babylm-main.22/) (Pulipaka & Barak, BabyLM 2026)
ACL