Accelerating Bangla NLP Tasks with Automatic Mixed Precision: Resource-Efficient Training Preserving Model Efficacy
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912738366717952 |
|---|---|
| author | Opi, Md Mehrab Hossain Khan, Sumaiya Rahman, Moshammad Farzana |
| author_facet | Opi, Md Mehrab Hossain Khan, Sumaiya Rahman, Moshammad Farzana |
| contents | Training models for Natural Language Processing (NLP) requires substantial computational resources and time, posing significant challenges, especially for NLP development in Bangla, where access to high-end hardware is often limited. In this work, we explore automatic mixed precision (AMP) training as a means to improve computational efficiency without sacrificing model performance. By leveraging a dynamic mix of 16-bit and 32-bit floating-point computations, AMP lowers GPU memory requirements and speeds up training without degrading model performance. We evaluate AMP across four standard Bangla NLP tasks, namely sentiment analysis, named entity recognition, error classification, and question answering, using four transformer-based models: BanglaBERT, BanglishBERT, XLM-R, and mBERT. Our results demonstrate that AMP accelerates training by 44.5% and reduces memory consumption by 17.6%, while maintaining F-1 score within 99.7% of the full-precision baselines. This empirical study highlights AMP's potential to democratize access to state-of-the-art NLP capabilities in hardware-constrained settings by lowering computational barriers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_00829 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Accelerating Bangla NLP Tasks with Automatic Mixed Precision: Resource-Efficient Training Preserving Model Efficacy Opi, Md Mehrab Hossain Khan, Sumaiya Rahman, Moshammad Farzana Computation and Language Artificial Intelligence Training models for Natural Language Processing (NLP) requires substantial computational resources and time, posing significant challenges, especially for NLP development in Bangla, where access to high-end hardware is often limited. In this work, we explore automatic mixed precision (AMP) training as a means to improve computational efficiency without sacrificing model performance. By leveraging a dynamic mix of 16-bit and 32-bit floating-point computations, AMP lowers GPU memory requirements and speeds up training without degrading model performance. We evaluate AMP across four standard Bangla NLP tasks, namely sentiment analysis, named entity recognition, error classification, and question answering, using four transformer-based models: BanglaBERT, BanglishBERT, XLM-R, and mBERT. Our results demonstrate that AMP accelerates training by 44.5% and reduces memory consumption by 17.6%, while maintaining F-1 score within 99.7% of the full-precision baselines. This empirical study highlights AMP's potential to democratize access to state-of-the-art NLP capabilities in hardware-constrained settings by lowering computational barriers. |
| title | Accelerating Bangla NLP Tasks with Automatic Mixed Precision: Resource-Efficient Training Preserving Model Efficacy |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2512.00829 |