Summary of Nlip_lab-iith Low-resource Mt System For Wmt24 Indic Mt Shared Task, by Pramit Sahoo et al.
NLIP_Lab-IITH Low-Resource MT System for WMT24 Indic MT Shared Task
by Pramit Sahoo, Maharaj Brahma, Maunendra Sankar Desarkar
First submitted to arxiv on: 4 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a system for the WMT 24 shared task of Low-Resource Indic Language Translation, focusing on finetuning pre-trained models for 22 scheduled Indian languages. The primary approach involves language-specific finetuning on a pre-trained model, achieving chrF2 scores of 50.6, 42.3, 54.9, and 66.3 on the official public test set for four participating language pairs. Additionally, the paper explores multilingual training with/without language grouping and layer-freezing. The authors share their code, models, and generated translations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a way to translate languages that don’t have much text available. It’s like trying to learn a new language when you only have a few words to work with! The researchers used special computer models to help them learn how to translate from one Indian language to another. They did really well, especially for some of the languages they tested. They even shared their code and translations so others can try it too! |
Keywords
» Artificial intelligence » Translation
