---
title: "STAR-IL: A Dataset for Style-Aware Machine — Shetye 2026"
description: "Machine translation of English e-commerce reviews into Indian languages often produces stiff, overly formal text."
authors: ["Ketaki Shetye", "Dipti Misra Sharma", "Parameswari Krishnamurthy"]
year: 2026
venue: "Proceedings of the Fifteenth Language Resources and Evaluation Conference"
source: "https://aclanthology.org/2026.lrec-1.691/"
doi: "10.63317/4oq85vioi2tu"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/shetye-2026-star-il-dataset-style-aware/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shetye-2026-star-il-dataset-style-aware/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/9/) / STAR-IL: A Dataset for Style-Aware Machine Translation of Product Reviews in Indian Languages

# STAR-IL: A Dataset for Style-Aware Machine Translation of Product Reviews in Indian Languages

**Authors:** Ketaki Shetye, [Dipti Misra Sharma](https://md.research.elamur.ai/free/en/authors/dipti-misra-sharma/), [Parameswari Krishnamurthy](https://md.research.elamur.ai/free/en/authors/parameswari-krishnamurthy/) · **Year:** 2026 · **Venue:** Proceedings of the Fifteenth Language Resources and Evaluation Conference · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.lrec-1.691/) · [PDF](https://aclanthology.org/2026.lrec-1.691.pdf) · [DOI 10.63317/4oq85vioi2tu](https://doi.org/10.63317/4oq85vioi2tu) · [OpenAlex](https://openalex.org/W7160095311)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14)

## Summary
Machine translation of English e-commerce reviews into Indian languages often produces stiff, overly formal text. It loses the casual register, slang, sarcasm and tone of the original, and domain-specific parallel data to address this is scarce. The authors build STAR-IL, a parallel corpus that pairs about 7,700 English reviews with human translations into eight languages: five Indo-Aryan and three Dravidian. The electronics reviews come from the IIT Patna/Flipkart set of Gupta et al. (2021), and the fashion reviews come from Myntra-based ShoppinAppReviews. Training data was created by post-editing output from Google Translate or Bhashaverse. The benchmark was translated from scratch and cross-reviewed twice. The guidelines favour colloquial phrasing, allow code-mixing, keep English technical terms and brand names, and require idiomatic equivalents. Source noise such as emojis and typos was deliberately preserved. Five multilingual models were benchmarked. Fine-tuning the strongest ones on STAR-IL improved results by an average of 5.77 BLEU and 3.78 COMET over baselines. The resource gives researchers a human-validated test set for register-preserving review translation in Indian languages.

## Key points
- **Coverage:** more than 55,000 translated samples, spanning the Indo-Aryan languages Hindi, Bengali, Marathi, Gujarati and Urdu as well as the Dravidian languages Tamil, Telugu and Kannada.
- **Domains and splits:**
  - Domain mix is about 71% electronics and 29% fashion.
  - The split is 90% training and 10% benchmark, with roughly 700 benchmark items per language.
- **Annotation:** 3–4 native-speaker translators per language pair worked in-house, using a two-track workflow:
  - post-editing for training data;
  - translation from scratch plus two independent cross-reviews for the benchmark.
- **Models evaluated:** IndicTrans2, Llama-3.1-8B, Llama-3.2-3B, Sarvam-Translate and Qwen3-8B, scored with BLEU, chrF, TER, COMET and BERTScore.
  - In domain-wise baselines, Sarvam-Translate and IndicTrans2 are generally strongest, and Qwen3-8B is weakest.
  - Fashion reviews are longer and more descriptive than electronics reviews.
- **Availability:** the dataset and annotation guidelines are public at github.com/ltrc/STAR-IL-Corpus.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

Topics: [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{shetye2026star,
  title = {{STAR-IL: A Dataset for Style-Aware Machine Translation of Product Reviews in Indian Languages}},
  author = {Shetye, Ketaki and Sharma, Dipti Misra and Krishnamurthy, Parameswari},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/4oq85vioi2tu},
  url = {https://doi.org/10.63317/4oq85vioi2tu}
}
```

- [← previous Stands to Reason: Investigating the Effect of Reasoning on Idiomaticity Detection](https://md.research.elamur.ai/free/en/papers/phelps-2026-stands-reason-investigating-effect-reasoning/)
- [next → Structured Entity Extraction from Hawaiian Television Chyrons Using Vision-Language Models](https://md.research.elamur.ai/free/en/papers/lynch-2026-structured-entity-extraction-hawaiian-television/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/9/)

## References

24 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Sweta Agrawal, António Farinhas, Ricardo Rei, and Andre Martins. 2024. Can automatic metrics assess high-quality translations? In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 14491–14502, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sweta+Agrawal%2C+Ant%C3%B3nio+Farinhas%2C+Ricardo+Rei%2C+and+Andre+Martins%2E+2024%2E+Can+automatic+metrics+assess+high%2Dquality+translations%3F+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in+Natural+Lan)
2. Meethu Mohan C, Sneha Shaji Punnan, and Jeena Kleenankandy. 2024. Improving few-shot prompting using cluster-based sample retrieval for medical NER in clinical text. In Proceedings of the 21st International Conference on Natural Language Processing (ICON), pages 37–44, AU-KBC Research Centre, Chenna… [find](https://scholar.google.com/scholar?q=Meethu+Mohan+C%2C+Sneha+Shaji+Punnan%2C+and+Jeena+Kleenankandy%2E+2024%2E+Improving+few%2Dshot+prompting+using+cluster%2Dbased+sample+retrieval+for+medical+NER+in+clinical+text%2E+In+Proceedings+of+the+21st+Interna)
3. Pranjal Chitale, Jay Gala, and Raj Dabre. 2024. An empirical study of in-context learning in LLMs for machine translation. In Findings of the Association for Computational Linguistics: ACL 2024, pages 7384–7406, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Pranjal+Chitale%2C+Jay+Gala%2C+and+Raj+Dabre%2E+2024%2E+An+empirical+study+of+in%2Dcontext+learning+in+LLMs+for+machine+translation%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2024%2C+pages)
4. Joseph L. Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological Bulletin, 76:378–382. [find](https://scholar.google.com/scholar?q=Joseph+L%2E+Fleiss%2E+1971%2E+Measuring+nominal+scale+agreement+among+many+raters%2E+Psychological+Bulletin%2C+76%3A378%E2%80%93382%2E)
5. Jay Gala, Pranjal A Chitale, A K Raghavan, Varun Gumma, Sumanth Doddapaneni, Aswanth Kumar M, Janki Atul Nawale, Anupama Sujatha, Ratish Puduppully, Vivek Raghavan, Pratyush Kumar, Mitesh M Khapra, Raj Dabre, and Anoop Kunchukuttan. 2023. Indictrans2: Towards high-quality and accessible machine tran… [find](https://scholar.google.com/scholar?q=Jay+Gala%2C+Pranjal+A+Chitale%2C+A+K+Raghavan%2C+Varun+Gumma%2C+Sumanth+Doddapaneni%2C+Aswanth+Kumar+M%2C+Janki+Atul+Nawale%2C+Anupama+Sujatha%2C+Ratish+Puduppully%2C+Vivek+Raghavan%2C+Pratyush+Kumar%2C+Mitesh+M+Khapra%2C+Ra) [our card](https://md.research.elamur.ai/free/en/papers/gala-2023-indictrans2-towards-high-quality-accessible/)
6. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao,… [find](https://scholar.google.com/scholar?q=Aaron+Grattafiori%2C+Abhimanyu+Dubey%2C+Abhinav+Jauhri%2C+Abhinav+Pandey%2C+Abhishek+Kadian%2C+Ahmad+Al%2DDahle%2C+Aiesha+Letman%2C+Akhil+Mathur%2C+Alan+Schelten%2C+Alex+Vaughan%2C+Amy+Yang%2C+Angela+Fan%2C+Anirudh+Goyal%2C+Anth)
7. Kamal Gupta, Soumya Chennabasavaraj, Nikesh Garera, and Asif Ekbal. 2021. Product review translation using phrase replacement and attention guided noise augmentation. In Proceedings of Machine Translation Summit XVIII: Research Track, pages 243–255, Virtual. Association for Machine Translation in th… [find](https://scholar.google.com/scholar?q=Kamal+Gupta%2C+Soumya+Chennabasavaraj%2C+Nikesh+Garera%2C+and+Asif+Ekbal%2E+2021%2E+Product+review+translation+using+phrase+replacement+and+attention+guided+noise+augmentation%2E+In+Proceedings+of+Machine+Transla)
8. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. [find](https://scholar.google.com/scholar?q=Edward+J%2E+Hu%2C+Yelong+Shen%2C+Phillip+Wallis%2C+Zeyuan+Allen%2DZhu%2C+Yuanzhi+Li%2C+Shean+Wang%2C+Lu+Wang%2C+and+Weizhu+Chen%2E+2021%2E+Lora%3A+Low%2Drank+adaptation+of+large+language+models%2E)
9. Vandan Mujadia and Dipti Misra Sharma. 2025. Bhashaverse : Translation ecosystem for indian subcontinent languages. [find](https://scholar.google.com/scholar?q=Vandan+Mujadia+and+Dipti+Misra+Sharma%2E+2025%2E+Bhashaverse+%3A+Translation+ecosystem+for+indian+subcontinent+languages%2E)
10. Zach Nussbaum, John X. Morris, Brandon Duderstadt, and Andriy Mulyar. 2025. Nomic embed: Training a reproducible long context text embedder. [find](https://scholar.google.com/scholar?q=Zach+Nussbaum%2C+John+X%2E+Morris%2C+Brandon+Duderstadt%2C+and+Andriy+Mulyar%2E+2025%2E+Nomic+embed%3A+Training+a+reproducible+long+context+text+embedder%2E) [our card](https://md.research.elamur.ai/free/en/papers/nussbaum-2024-nomic-embed-training-reproducible-long/)
11. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL ’02, page 311–318, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Kishore+Papineni%2C+Salim+Roukos%2C+Todd+Ward%2C+and+Wei%2DJing+Zhu%2E+2002%2E+Bleu%3A+a+method+for+automatic+evaluation+of+machine+translation%2E+In+Proceedings+of+the+40th+Annual+Meeting+on+Association+for+Computat) [our card](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/)
12. David Ponce and Thierry Etchegoyhen. 2025. In-context learning vs. instruction tuning: The case of small and multilingual language models. [find](https://scholar.google.com/scholar?q=David+Ponce+and+Thierry+Etchegoyhen%2E+2025%2E+In%2Dcontext+learning+vs%2E+instruction+tuning%3A+The+case+of+small+and+multilingual+language+models%2E)
13. Maja Popović. 2015. chrF: character n-gram Fscore for automatic MT evaluation. In Proceedings of the Tenth Workshop on Statistical Machine Translation, pages 392–395, Lisbon, Portugal. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Maja+Popovi%C4%87%2E+2015%2E+chrF%3A+character+n%2Dgram+Fscore+for+automatic+MT+evaluation%2E+In+Proceedings+of+the+Tenth+Workshop+on+Statistical+Machine+Translation%2C+pages+392%E2%80%93395%2C+Lisbon%2C+Portugal%2E+Association+for)
14. Shenbin Qian, Constantin Orasan, Diptesh Kanojia, and Félix Do Carmo. 2024. Are large language models state-of-the-art quality estimators for machine translation of user-generated content? In Proceedings of the Eleventh Workshop on Asian Translation (WAT 2024), pages 45–55, Miami, Florida, USA. Asso… [find](https://scholar.google.com/scholar?q=Shenbin+Qian%2C+Constantin+Orasan%2C+Diptesh+Kanojia%2C+and+F%C3%A9lix+Do+Carmo%2E+2024%2E+Are+large+language+models+state%2Dof%2Dthe%2Dart+quality+estimators+for+machine+translation+of+user%2Dgenerated+content%3F+In+Proceedi)
15. Ricardo Rei, José G. C. de Souza, Duarte Alves, Chrysoula Zerva, Ana C Farinha, Taisiya Glushkova, Alon Lavie, Luisa Coheur, and André F. T. Martins. 2022. COMET-22: Unbabel-IST 2022 submission for the metrics shared task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages… [find](https://scholar.google.com/scholar?q=Ricardo+Rei%2C+Jos%C3%A9+G%2E+C%2E+de+Souza%2C+Duarte+Alves%2C+Chrysoula+Zerva%2C+Ana+C+Farinha%2C+Taisiya+Glushkova%2C+Alon+Lavie%2C+Luisa+Coheur%2C+and+Andr%C3%A9+F%2E+T%2E+Martins%2E+2022%2E+COMET%2D22%3A+Unbabel%2DIST+2022+submission+for+th) [our card](https://md.research.elamur.ai/free/en/papers/rei-2022-comet-22-unbabel-ist-2022/)
16. Hadeel Saadany and Constantin Orasan. 2020. Is it great or terrible? preserving sentiment in neural machine translation of Arabic reviews. In Proceedings of the Fifth Arabic Natural Language Processing Workshop, pages 24–37, Barcelona, Spain (Online). Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Hadeel+Saadany+and+Constantin+Orasan%2E+2020%2E+Is+it+great+or+terrible%3F+preserving+sentiment+in+neural+machine+translation+of+Arabic+reviews%2E+In+Proceedings+of+the+Fifth+Arabic+Natural+Language+Processin)
17. Sarvam AI Team. 2024. SARVAM - TRANSLATE. [find](https://scholar.google.com/scholar?q=Sarvam+AI+Team%2E+2024%2E+SARVAM+%2D+TRANSLATE%2E)
18. Matthew Snover, Bonnie Dorr, Rich Schwartz, Linnea Micciulla, and John Makhoul. 2006. A study of translation edit rate with targeted human annotation. In Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers, pages 223–231, Cambridge, Massachu… [find](https://scholar.google.com/scholar?q=Matthew+Snover%2C+Bonnie+Dorr%2C+Rich+Schwartz%2C+Linnea+Micciulla%2C+and+John+Makhoul%2E+2006%2E+A+study+of+translation+edit+rate+with+targeted+human+annotation%2E+In+Proceedings+of+the+7th+Conference+of+the+Assoc) [our card](https://md.research.elamur.ai/free/en/papers/snover-2006-study-translation-edit-rate-targeted/)
19. Sanford B. Steever, editor. 2019. The Dravidian Languages, 2nd edition. Routledge. [find](https://scholar.google.com/scholar?q=Sanford+B%2E+Steever%2C+editor%2E+2019%2E+The+Dravidian+Languages%2C+2nd+edition%2E+Routledge%2E)
20. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Etienne Pot, Ivo Penche… [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Aishwarya+Kamath%2C+Johan+Ferret%2C+Shreya+Pathak%2C+Nino+Vieillard%2C+Ramona+Merhej%2C+Sarah+Perrin%2C+Tatiana+Matejovicova%2C+Alexandre+Ram%C3%A9%2C+Morgane+Rivi%C3%A8re%2C+Louis+Rouillard%2C+Thomas+Mesnard%2C+Geoffrey)
21. Vandana Yadav, Parul Verma, and Vinodini Katiyar. 2021. E-commerce product reviews using aspect based hindi sentiment analysis. In 2021 International Conference on Computer Communication and Informatics (ICCCI), pages 1–8. [find](https://scholar.google.com/scholar?q=Vandana+Yadav%2C+Parul+Verma%2C+and+Vinodini+Katiyar%2E+2021%2E+E%2Dcommerce+product+reviews+using+aspect+based+hindi+sentiment+analysis%2E+In+2021+International+Conference+on+Computer+Communication+and+Informati)
22. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jing Zhou, Jin… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Anfeng+Li%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Gao%2C+Chengen+Huang%2C+Chenxu+Lv%2C+Chujie+Zheng%2C+Dayiheng+Liu%2C+Fan+Zhou%2C+Fei+Huang%2C+Feng+Hu%2C+Hao+Ge%2C+Haoran+Wei%2C+Hua) [our card](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/)
23. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with bert. 11. [find](https://scholar.google.com/scholar?q=Tianyi+Zhang%2C+Varsha+Kishore%2C+Felix+Wu%2C+Kilian+Q%2E+Weinberger%2C+and+Yoav+Artzi%2E+2020%2E+Bertscore%3A+Evaluating+text+generation+with+bert%2E+11%2E)
24. Language Resource References Arnob and Noor Mairukh Khan. 2024. Shoppin-gAppReviews Dataset. Mendeley Data. 12. Appendix 12.1. [find](https://scholar.google.com/scholar?q=Language+Resource+References+Arnob+and+Noor+Mairukh+Khan%2E+2024%2E+Shoppin%2DgAppReviews+Dataset%2E+Mendeley+Data%2E+12%2E+Appendix+12%2E1%2E)