SPRING Lab IITM's submission to Low Resource Indic Language Translation Shared Task
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912112837656576 |
|---|---|
| author | Sayed, Hamees Joglekar, Advait Umesh, Srinivasan |
| author_facet | Sayed, Hamees Joglekar, Advait Umesh, Srinivasan |
| contents | We develop a robust translation model for four low-resource Indic languages: Khasi, Mizo, Manipuri, and Assamese. Our approach includes a comprehensive pipeline from data collection and preprocessing to training and evaluation, leveraging data from WMT task datasets, BPCC, PMIndia, and OpenLanguageData. To address the scarcity of bilingual data, we use back-translation techniques on monolingual datasets for Mizo and Khasi, significantly expanding our training corpus. We fine-tune the pre-trained NLLB 3.3B model for Assamese, Mizo, and Manipuri, achieving improved performance over the baseline. For Khasi, which is not supported by the NLLB model, we introduce special tokens and train the model on our Khasi corpus. Our training involves masked language modelling, followed by fine-tuning for English-to-Indic and Indic-to-English translations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_00727 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SPRING Lab IITM's submission to Low Resource Indic Language Translation Shared Task Sayed, Hamees Joglekar, Advait Umesh, Srinivasan Computation and Language Artificial Intelligence We develop a robust translation model for four low-resource Indic languages: Khasi, Mizo, Manipuri, and Assamese. Our approach includes a comprehensive pipeline from data collection and preprocessing to training and evaluation, leveraging data from WMT task datasets, BPCC, PMIndia, and OpenLanguageData. To address the scarcity of bilingual data, we use back-translation techniques on monolingual datasets for Mizo and Khasi, significantly expanding our training corpus. We fine-tune the pre-trained NLLB 3.3B model for Assamese, Mizo, and Manipuri, achieving improved performance over the baseline. For Khasi, which is not supported by the NLLB model, we introduce special tokens and train the model on our Khasi corpus. Our training involves masked language modelling, followed by fine-tuning for English-to-Indic and Indic-to-English translations. |
| title | SPRING Lab IITM's submission to Low Resource Indic Language Translation Shared Task |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2411.00727 |