---
title: "AssamLegalTrans — Singh 2026"
description: "Judgments of India's higher courts are written in English, so Assamese speakers who do not read English struggle to access decisions that affect them."
authors: ["Telem Joyson Singh", "Hemanta Baruah", "Sanasam Ranbir Singh", "Anindita Talukdar", "Nasrin Shahnaz", "Okram Jimmy Singh", "Priyankoo Sarmah", "Pallav Kumar Dutta", "Sukumar Nandi", "Pranab Duara"]
year: 2026
venue: "Proceedings of the Fifteenth Language Resources and Evaluation Conference"
source: "https://aclanthology.org/2026.lrec-1.386/"
doi: "10.63317/5q53i6shk3nm"
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/papers/singh-2026-assamlegaltrans-parallel-corpus-benchmark-analysis/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/singh-2026-assamlegaltrans-parallel-corpus-benchmark-analysis/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2026](https://md.research.elamur.ai/free/papers/2026/) / AssamLegalTrans: A Parallel Corpus, Benchmark and Analysis for English-Assamese Machine Translation of Legal Judgments

# AssamLegalTrans: A Parallel Corpus, Benchmark and Analysis for English-Assamese Machine Translation of Legal Judgments

**Authors:** Telem Joyson Singh, Hemanta Baruah, Sanasam Ranbir Singh, Anindita Talukdar, Nasrin Shahnaz, Okram Jimmy Singh, Priyankoo Sarmah, Pallav Kumar Dutta, Sukumar Nandi, Pranab Duara · **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-1.386/) · [PDF](https://aclanthology.org/2026.lrec-1.386.pdf) · [DOI 10.63317/5q53i6shk3nm](https://doi.org/10.63317/5q53i6shk3nm) · [OpenAlex](https://openalex.org/W7160155955)

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

## Summary
Judgments of India's higher courts are written in English, so Assamese speakers who do not read English struggle to access decisions that affect them. Machine translation could help, but no public legal-domain parallel data has existed for English–Assamese. The authors build AssamLegalTrans, a corpus of more than 55,000 sentence pairs taken from about 500 civil, criminal and other rulings issued by the Supreme Court of India and the Gauhati High Court. Every pair was translated and checked by humans. They then benchmark multilingual systems, including NLLB-200 and Sarvam-Translate, both without adaptation and after fine-tuning on the corpus, and compare them with commercial services such as Google Translate. Fine-tuning on the legal data produces large gains: the adapted NLLB model reaches 36.29 BLEU, well above its zero-shot result. An error analysis shows where systems still fail. Problems include official legal terminology, choosing between transliterating and translating names, expanding abbreviations, and recasting English passive clauses into Assamese active SOV order. The released resource gives a reproducible starting point for legal MT and for better access to justice in Assamese.

## Key points
- **Resource:** AssamLegalTrans contains more than 55,000 manually translated and validated English–Assamese sentence pairs sourced from roughly 500 decisions handed down by the Supreme Court of India and the Gauhati High Court. The authors describe it as the first parallel corpus of its kind and make it publicly available.
- **Quality control:** two native Assamese speakers checked each alignment independently, one with an English background and one with a legal background. Their agreement was reported as a Cohen's kappa of 90. A third translator resolved disagreements by majority vote.
- **Benchmark:** NLLB-200 and Sarvam-Translate were tested zero-shot and fine-tuned, alongside Google Translate. Fine-tuned NLLB achieved 36.29 BLEU, a clear gain over its zero-shot version.
- **Document structure:** judgments are split into a Preamble and a Main Body.
  - The Preamble is dense with named entities, acronyms and case metadata.
  - The Main Body has distinct rhetorical sections: facts, arguments, reasoning and decision. These contain long, multi-clause sentences and terms with fixed official Assamese equivalents.
- **Error categories analysed:** legal terminology adherence (e.g., "assessee"), transliteration vs. translation of names ("Bhagat Singh" vs. "High Court"), abbreviation expansion ("Art." → "Article"), and passive-to-active voice restructuring for SOV Assamese.

*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/shelves/linguistics/) · [Machine translation](https://md.research.elamur.ai/free/shelves/machine-translation/) · [Law](https://md.research.elamur.ai/free/shelves/law/)

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

## Cite

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

```bibtex
@inproceedings{singh2026assamlegaltrans,
  title = {{AssamLegalTrans: A Parallel Corpus, Benchmark and Analysis for English-Assamese Machine Translation of Legal Judgments}},
  author = {Singh, Telem Joyson and Baruah, Hemanta and Singh, Sanasam Ranbir and Talukdar, Anindita and Shahnaz, Nasrin and Singh, Okram Jimmy and Sarmah, Priyankoo and Dutta, Pallav Kumar and Nandi, Sukumar and Duara, Pranab},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/5q53i6shk3nm},
  url = {https://doi.org/10.63317/5q53i6shk3nm}
}
```

- [← previous ASCAT: Arabic Scientific Benchmark for Advanced Translation Evaluation](https://md.research.elamur.ai/free/papers/sibaee-2026-ascat-arabic-scientific-benchmark-advanced/)
- [next → Assessing and Improving Punctuation Robustness in English-Marathi Machine Translation](https://md.research.elamur.ai/free/papers/shejole-2026-assessing-improving-punctuation-robustness-english/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/papers/2026/)

## References

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

1. Gunjan Agrahari. 2015. Languages in administration of justice. Journal of Legal Studies, 3:161. [find](https://scholar.google.com/scholar?q=Gunjan+Agrahari%2E+2015%2E+Languages+in+administration+of+justice%2E+Journal+of+Legal+Studies%2C+3%3A161%2E)
2. Sarvam AI. 2025. Sarvam - translate. Sarvam Translate Blog. Accessed: June 29, 2025. [find](https://scholar.google.com/scholar?q=Sarvam+AI%2E+2025%2E+Sarvam+%2D+translate%2E+Sarvam+Translate+Blog%2E+Accessed%3A+June+29%2C+2025%2E)
3. Vicent Briva-Iglesias, Joao Lucas Cavalheiro Camargo, and Gokhan Dogru. 2024. Large language models "ad referendum": How good are they at machine translation in the legal domain? [find](https://scholar.google.com/scholar?q=Vicent+Briva%2DIglesias%2C+Joao+Lucas+Cavalheiro+Camargo%2C+and+Gokhan+Dogru%2E+2024%2E+Large+language+models+%22ad+referendum%22%3A+How+good+are+they+at+machine+translation+in+the+legal+domain%3F)
4. Marta R Costa-Jussa, James Cross, Onur Celebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, et al. 2022. No language left behind: Scaling human-centered machine translation. arXiv preprint arXiv:2207.04672. [↗](https://arxiv.org/abs/2207.04672)
5. Flavia De Camillis, Egon W. Stemle, Elena Chiocchetti, and Francesco Fernicola. 2023. The MT@BZ corpus: machine translation & legal language. In Proceedings of the 24th Annual Conference of the European Association for Machine Translation, pages 171--180, Tampere, Finland. European Association for Machine Translation. [find](https://scholar.google.com/scholar?q=Flavia+De+Camillis%2C+Egon+W%2E+Stemle%2C+Elena+Chiocchetti%2C+and+Francesco+Fernicola%2E+2023%2E+The+MT%40BZ+corpus%3A+machine+translation+%26+legal+language%2E+In+Proceedings+of+the+24th+Annual+Conference+of+the+Europe)
6. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Edward+J+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+2022%2E+LoRA%3A+Low%2Drank+adaptation+of+large+language+models%2E+In+International+Conference+on+L)
7. Bui Thanh Hung, Nguyen Le Minh, and Akira Shimazu. 2013. Translating legal sentence by segmentation and rule selection. International Journal on Natural Language Computing, 2(4):35--54. [↗](https://doi.org/10.5121/ijnlc.2013.2403)
8. Julia Ive, Lucia Specia, Sara Szoc, Tom Vanallemeersch, Joachim Van den Bogaert, Eduardo Farah, Christine Maroti, Artur Ventura, and Maxim Khalilov. 2020. A post-editing dataset in the legal domain: Do we underestimate neural machine translation quality? In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 3692--3697, Marseille, France. European Language Resources Association. [find](https://scholar.google.com/scholar?q=Julia+Ive%2C+Lucia+Specia%2C+Sara+Szoc%2C+Tom+Vanallemeersch%2C+Joachim+Van+den+Bogaert%2C+Eduardo+Farah%2C+Christine+Maroti%2C+Artur+Ventura%2C+and+Maxim+Khalilov%2E+2020%2E+A+post%2Dediting+dataset+in+the+legal+domain%3A+D)
9. Prathamesh Kalamkar, Aman Tiwari, Astha Agarwal, Saurabh Karn, Smita Gupta, Vivek Raghavan, and Ashutosh Modi. 2022. Corpus for automatic structuring of legal documents. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 4420--4429, Marseille, France. European Language Resources Association. [find](https://scholar.google.com/scholar?q=Prathamesh+Kalamkar%2C+Aman+Tiwari%2C+Astha+Agarwal%2C+Saurabh+Karn%2C+Smita+Gupta%2C+Vivek+Raghavan%2C+and+Ashutosh+Modi%2E+2022%2E+Corpus+for+automatic+structuring+of+legal+documents%2E+In+Proceedings+of+the+Thirteen)
10. Tom Kocmi, Eleftherios Avramidis, Rachel Bawden, Ondrej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Marzena Karpinska, Philipp Koehn, Benjamin Marie, Christof Monz, Kenton Murray, Masaaki Nagata, Martin Popel, Maja Popovic, Mariya Shmatova, Steinthor Steingrimsson, and Vilem Zouhar. 2024. Findings of the WMT24 general machine translation shared task: The LLM era is here but MT is not solved yet. In Proceedings of the Ninth Conference on Machine Translation, pages 1--46, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Tom+Kocmi%2C+Eleftherios+Avramidis%2C+Rachel+Bawden%2C+Ondrej+Bojar%2C+Anton+Dvorkovich%2C+Christian+Federmann%2C+Mark+Fishel%2C+Markus+Freitag%2C+Thamme+Gowda%2C+Roman+Grundkiewicz%2C+Barry+Haddow%2C+Marzena+Karpinska%2C+Ph) [our card](https://md.research.elamur.ai/free/papers/kocmi-2024-findings-wmt24-general-machine-translation/)
11. Tom Kocmi, Eleftherios Avramidis, Rachel Bawden, Ondrej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Philipp Koehn, Benjamin Marie, Christof Monz, Makoto Morishita, Kenton Murray, Masaaki Nagata, Toshiaki Nakazawa, Martin Popel, Maja Popovic, Mariya Shmatova, and Jun Suzuki. 2023. Findings of the 2023 conference on machine translation (WMT23): LLMs are here but not quite there yet. In Proceedings of the Eighth Conference on Machine Translation, pages 1--42, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Tom+Kocmi%2C+Eleftherios+Avramidis%2C+Rachel+Bawden%2C+Ondrej+Bojar%2C+Anton+Dvorkovich%2C+Christian+Federmann%2C+Mark+Fishel%2C+Markus+Freitag%2C+Thamme+Gowda%2C+Roman+Grundkiewicz%2C+Barry+Haddow%2C+Philipp+Koehn%2C+Benjam)
12. Sayan Mahapatra, Debtanu Datta, Shubham Soni, Adrijit Goswami, and Saptarshi Ghosh. 2025. Milpac: A novel benchmark for evaluating translation of legal text to indian languages. ACM Trans. Asian Low-Resour. Lang. Inf. Process., 24(8). [↗](https://doi.org/10.1145/3748313)
13. Ruben Martinez-Dominguez, Matiss Rikters, Arturs Vasilevskis, Marcis Pinnis, and Paula Reichenberg. 2020. Customized neural machine translation systems for the Swiss legal domain. In Proceedings of the 14th Conference of the Association for Machine Translation in the Americas (Volume 2: User Track), pages 217--223, Virtual. Association for Machine Translation in the Americas. [find](https://scholar.google.com/scholar?q=Ruben+Martinez%2DDominguez%2C+Matiss+Rikters%2C+Arturs+Vasilevskis%2C+Marcis+Pinnis%2C+and+Paula+Reichenberg%2E+2020%2E+Customized+neural+machine+translation+systems+for+the+Swiss+legal+domain%2E+In+Proceedings+of+th)
14. Shubham Kumar Nigam, Tanmay Dubey, Govind Sharma, Noel Shallum, Kripabandhu Ghosh, and Arnab Bhattacharya. 2025. LegalSeg: Unlocking the structure of Indian legal judgments through rhetorical role classification. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 1129--1144, Albuquerque, New Mexico. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Shubham+Kumar+Nigam%2C+Tanmay+Dubey%2C+Govind+Sharma%2C+Noel+Shallum%2C+Kripabandhu+Ghosh%2C+and+Arnab+Bhattacharya%2E+2025%2E+LegalSeg%3A+Unlocking+the+structure+of+Indian+legal+judgments+through+rhetorical+role+cla)
15. 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 of the Association for Computational Linguistics, pages 311-- 318, Philadelphia, Pennsylvania, USA. Association for Computational Linguistics. [↗](https://doi.org/10.3115/1073083.1073135) [our card](https://md.research.elamur.ai/free/papers/papineni-2002-bleu-method-automatic-evaluation-machine/)
16. Maja Popovic. 2017. chrF++: words helping character n-grams. In Proceedings of the Second Conference on Machine Translation, pages 612--618, Copenhagen, Denmark. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Maja+Popovic%2E+2017%2E+chrF%2B%2B%3A+words+helping+character+n%2Dgrams%2E+In+Proceedings+of+the+Second+Conference+on+Machine+Translation%2C+pages+612%2D%2D618%2C+Copenhagen%2C+Denmark%2E+Association+for+Computational+Linguist) [our card](https://md.research.elamur.ai/free/papers/popovic-2017-chrf-words-helping-character-n/)
17. Shabdapurush Poudel, Bal Krishna Bal, and Praveen Acharya. 2024. Bidirectional English-Nepali machine translation(MT) system for legal domain. In Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024, pages 53--58, Torino, Italia. ELRA and ICCL. [find](https://scholar.google.com/scholar?q=Shabdapurush+Poudel%2C+Bal+Krishna+Bal%2C+and+Praveen+Acharya%2E+2024%2E+Bidirectional+English%2DNepali+machine+translation%28MT%29+system+for+legal+domain%2E+In+Proceedings+of+the+3rd+Annual+Meeting+of+the+Special+I)
18. Telem Joyson Singh, Sanasam Ranbir Singh, Deepen Naorem, and Priyankoo Sarmah. 2025. Chain-of-morphemes tuning: Injecting morphology in llm-based machine translation. In 2025 International Joint Conference on Neural Networks (IJCNN), pages 1--8. [find](https://scholar.google.com/scholar?q=Telem+Joyson+Singh%2C+Sanasam+Ranbir+Singh%2C+Deepen+Naorem%2C+and+Priyankoo+Sarmah%2E+2025%2E+Chain%2Dof%2Dmorphemes+tuning%3A+Injecting+morphology+in+llm%2Dbased+machine+translation%2E+In+2025+International+Joint+Confe)
19. 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, Massachusetts, USA. Association for Machine Translation in the Americas. [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/papers/snover-2006-study-translation-edit-rate-targeted/)
20. Gemma Team. 2025. Gemma 3 technical report. ArXiv, abs/2503.19786. [↗](https://arxiv.org/abs/2503.19786)
21. OpenAI Team. 2024. Gpt-4 technical report. [↗](https://doi.org/10.4230/lipics.cosit.2024.11) [our card](https://md.research.elamur.ai/free/papers/openai-2023-gpt-4-technical-report/)
22. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander Rush. 2020. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 38--45, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.emnlp-demos.6) [our card](https://md.research.elamur.ai/free/papers/wolf-2020-transformers-state-art-natural-language/)