# BanglaSTEM: A Parallel Corpus for Technical Domain Bangla-English Translation

arXiv: https://arxiv.org/abs/2511.03498 · HTML: https://mlsanity.com/paper/2511.03498/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Builds on (most cited first, 9 of 9)

- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages](https://mlsanity.com/paper/2305.16307/) (2023)
- [Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages](https://mlsanity.com/paper/2104.05596/) (2021)
- [BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla](https://mlsanity.com/paper/2101.00204/) (2021)
- [A Survey of Domain Adaptation for Neural Machine Translation](https://mlsanity.com/paper/1806.00258/) (2018)
- [Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation](https://mlsanity.com/paper/2009.09359/) (2020)
- [Domain Adaptation of Neural Machine Translation by Lexicon Induction](https://mlsanity.com/paper/1906.00376/) (2019)
- [mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation](https://mlsanity.com/paper/2410.15037/) (2024)

## Built on by (most cited first, 1 of 1)

- [Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts](https://mlsanity.com/paper/2605.28042/) (2026)

## Abstract (arXiv)

Large language models work well for technical problem solving in English but perform poorly when the same questions are asked in Bangla. A simple solution would be to translate Bangla questions into English first and then use these models. However, existing Bangla-English translation systems struggle with technical terms. They often mistranslate specialized vocabulary, which changes the meaning of the problem and leads to wrong answers. We present BanglaSTEM, a dataset of 5,000 carefully selected Bangla-English sentence pairs from STEM fields including computer science, mathematics, physics, chemistry, and biology. We generated over 12,000 translations using language models and then used human evaluators to select the highest quality pairs that preserve technical terminology correctly. We train a T5-based translation model on BanglaSTEM and test it on two tasks: generating code and solving math problems. Our results show significant improvements in translation accuracy for technical content, making it easier for Bangla speakers to use English-focused language models effectively. Both the BanglaSTEM dataset and the trained translation model are publicly released at https://huggingface.co/reyazul/BanglaSTEM-T5.