arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.07457cs.CL
收藏

从巴西葡萄牙语到欧洲葡萄牙语

From Brazilian Portuguese to European Portuguese

Instituto Superior Técnico(高等技术学院);Universidade de Lisboa(里斯本大学);INESC-ID

João Sanches, Rui Ribeiro, Luísa Coheur

AI总结:

针对巴葡与欧葡资源不均影响欧葡翻译质量的问题,研究者依托神经技术构建巴葡转欧葡翻译系统,整理含500句的双参考黄金测试集,用平行语料微调多类大模型并结合自动、人工评估与ChatGPT 3.5 Turbo对比验证效果。

摘要:

巴西葡萄牙语与欧洲葡萄牙语是同一种语言的两种变体,尽管相似度极高,但仍存在诸多差异。然而,两种变体的可用资源存在显著失衡,巴西葡萄牙语的资源更为丰富,这种资源不均会影响欧洲葡萄牙语使用者可获得的翻译服务质量。为解决这一问题,我们提出构建一套巴西葡萄牙语转欧洲葡萄牙语的翻译系统,该系统依托神经架构与模型领域的最新进展研发。为评估这类系统的性能,我们人工整理了一个包含5个不同主题共500个句子的黄金测试集,测试集中每个句子都配有两条不同的参考译文,可便捷用于未来翻译模型的评估。我们利用从电影字幕及TED Talks演讲稿中提取的巴葡、欧葡平行语料,对现有大语言模型进行微调,测试了多种模型的效果。评估过程既采用了传统自动指标,也开展了人工评估,此外还将所有模型与当前表现最优的ChatGPT 3.5 Turbo进行了对比。

英文摘要:

Brazilian Portuguese and European Portuguese are two varieties of the same language and, despite their close similarities, they exhibit several differences. However, there is a significant disproportion in the availability of resources between the two variants, with Brazilian Portuguese having more abundant resources. This inequity can impact the quality of translation services accessible to European Portuguese speakers. To address this issue, we propose the development of a Brazilian Portuguese to European Portuguese translation system, leveraging recent advancements in neural architectures and models. To evaluate the performance of such systems, we manually curated a gold test set comprising 500 sentences across five different topics. Each sentence in the gold test set has two distinct references, facilitating a straightforward evaluation of future translation models. We experimented with various models by fine-tuning existing Large Language Models using parallel data extracted from movie subtitles and TED Talks transcripts in both Brazilian and European Portuguese. Our evaluation involved the use of conventional automatic metrics as well as a human evaluation. In addition, all models were compared against ChatGPT 3.5 Turbo, which currently yields the best results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑