针对低资源印地语翻译，提出基于微调的高效模型，性能优于基线。
NLIP_Lab-IITH Low-Resource MT System for WMT24 Indic MT Shared Task
- 基于预训练模型进行语言特定微调，提升低资源翻译效果。
- 在英-阿萨姆、英-卡哈等四对语言上达到最高66.3的chrF2得分。
- 开源代码与模型，适合低资源语言研究者参考使用。
本文介绍我们在WMT 24低资源印地语翻译共享任务中的系统。我们关注eng ↔ {as, kha, lus, mni} 四对语言对。受对齐增强方法启发，通过预训练目标对嵌入进行对齐，探索22种印度语言的微调策略。主系统基于预训练模型的语言特定微调，在官方公开测试集上取得eng→as、eng→kha、eng→lus、eng→mni的chrF2分数分别为50.6、42.3、54.9和66.3。同时探索了分组与非分组多语言训练，以及层冻结策略。代码、模型及生成译文已开源：https://github.com/pramitsahoo/WMT2024-LRILT。
原文摘要 · Abstract (English)
In this paper, we describe our system for the WMT 24 shared task of Low-Resource Indic Language Translation. We consider eng $\leftrightarrow$ {as, kha, lus, mni} as participating language pairs. In this shared task, we explore the finetuning of a pre-trained model motivated by the pre-trained objective of aligning embeddings closer by alignment augmentation \cite{lin-etal-2020-pre} for 22 scheduled Indian languages. Our primary system is based on language-specific finetuning on a pre-trained model. We achieve chrF2 scores of 50.6, 42.3, 54.9, and 66.3 on the official public test set for eng$\rightarrow$as, eng$\rightarrow$kha, eng$\rightarrow$lus, eng$\rightarrow$mni respectively. We also explore multilingual training with/without language grouping and layer-freezing. Our code, models, and generated translations are available here: https://github.com/pramitsahoo/WMT2024-LRILT.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。