Scholarlink

This report presents the evaluation results of the Tibetan-Chinese machine translation task conducted by the National Language Resources Monitoring and Research Center for Minority Languages at the 20th Conference on Machine Translation (CCMT2024). The translation system described in this paper is based on the LLaMA2-7B architecture, with specific secondary pre-training and supervised fine-tuning tailored to the translation task. The results demonstrate that this approach effectively improves the performance of Tibetan-Chinese machine translation. Additionally, this paper employs a parameter grid search method to investigate the impact of different parameter combinations on translation performance.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CCMT2024 Tibetan-Chinese Machine Translation Evaluation Technical Report

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Wenhao Zhuang,
  • Dawa Cairen,
  • Pengmao Cairang,
  • Yuan Sun

摘要

This report presents the evaluation results of the Tibetan-Chinese machine translation task conducted by the National Language Resources Monitoring and Research Center for Minority Languages at the 20th Conference on Machine Translation (CCMT2024). The translation system described in this paper is based on the LLaMA2-7B architecture, with specific secondary pre-training and supervised fine-tuning tailored to the translation task. The results demonstrate that this approach effectively improves the performance of Tibetan-Chinese machine translation. Additionally, this paper employs a parameter grid search method to investigate the impact of different parameter combinations on translation performance.