@inproceedings{shetye-etal-2026-star,
title = "{STAR}-{IL}: A Dataset for Style-Aware Machine Translation of Product Reviews in {I}ndian Languages",
author = "Shetye, Ketaki and
Sharma, Dipti Misra and
Krishnamurthy, Parameswari",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.691/",
doi = "10.63317/4oq85vioi2tu",
pages = "8780--8793",
abstract = "Product reviews on e-commerce platforms are a critical form of user-generated content that influence consumer decisions. However, these reviews are predominantly in English, creating a significant accessibility barrier for users who are not fluent in English. When translating into major Indian languages using the current models, the outputs often fail to capture domain-specific features and colloquial style, resulting in stylistically unnatural texts. To address this gap, we introduce \textbf{STAR-IL}, a human-annotated, multilingual, parallel corpus for style-aware translation of product reviews. We evaluate the performance of several state-of-the-art models on our dataset for the task of product review translation. Our experiments show that models fine-tuned on STAR-IL achieve significant average performance gain of \textbf{5.77} points in BLEU and \textbf{3.78} points in COMET, when compared to their baselines, across all languages. Our dataset provides a valuable benchmark for future research in style-aware product review translation. The STAR-IL dataset is publicly available at \url{https://github.com/ltrc/STAR-IL-Corpus}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shetye-etal-2026-star">
<titleInfo>
<title>STAR-IL: A Dataset for Style-Aware Machine Translation of Product Reviews in Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ketaki</namePart>
<namePart type="family">Shetye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="given">Misra</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Product reviews on e-commerce platforms are a critical form of user-generated content that influence consumer decisions. However, these reviews are predominantly in English, creating a significant accessibility barrier for users who are not fluent in English. When translating into major Indian languages using the current models, the outputs often fail to capture domain-specific features and colloquial style, resulting in stylistically unnatural texts. To address this gap, we introduce STAR-IL, a human-annotated, multilingual, parallel corpus for style-aware translation of product reviews. We evaluate the performance of several state-of-the-art models on our dataset for the task of product review translation. Our experiments show that models fine-tuned on STAR-IL achieve significant average performance gain of 5.77 points in BLEU and 3.78 points in COMET, when compared to their baselines, across all languages. Our dataset provides a valuable benchmark for future research in style-aware product review translation. The STAR-IL dataset is publicly available at https://github.com/ltrc/STAR-IL-Corpus.</abstract>
<identifier type="citekey">shetye-etal-2026-star</identifier>
<identifier type="doi">10.63317/4oq85vioi2tu</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.691/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>8780</start>
<end>8793</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T STAR-IL: A Dataset for Style-Aware Machine Translation of Product Reviews in Indian Languages
%A Shetye, Ketaki
%A Sharma, Dipti Misra
%A Krishnamurthy, Parameswari
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F shetye-etal-2026-star
%X Product reviews on e-commerce platforms are a critical form of user-generated content that influence consumer decisions. However, these reviews are predominantly in English, creating a significant accessibility barrier for users who are not fluent in English. When translating into major Indian languages using the current models, the outputs often fail to capture domain-specific features and colloquial style, resulting in stylistically unnatural texts. To address this gap, we introduce STAR-IL, a human-annotated, multilingual, parallel corpus for style-aware translation of product reviews. We evaluate the performance of several state-of-the-art models on our dataset for the task of product review translation. Our experiments show that models fine-tuned on STAR-IL achieve significant average performance gain of 5.77 points in BLEU and 3.78 points in COMET, when compared to their baselines, across all languages. Our dataset provides a valuable benchmark for future research in style-aware product review translation. The STAR-IL dataset is publicly available at https://github.com/ltrc/STAR-IL-Corpus.
%R 10.63317/4oq85vioi2tu
%U https://aclanthology.org/2026.lrec-1.691/
%U https://doi.org/10.63317/4oq85vioi2tu
%P 8780-8793
Markdown (Informal)
[STAR-IL: A Dataset for Style-Aware Machine Translation of Product Reviews in Indian Languages](https://aclanthology.org/2026.lrec-1.691/) (Shetye et al., LREC 2026)
ACL