扩展 FLORES+ 基准以涵盖更多低资源场景：葡萄牙语-Emakhuwa 机器翻译评估
Expanding FLORES+ Benchmark for more Low-Resource Settings: Portuguese-Emakhuwa Machine Translation Evaluation
AI总结：
本文扩展了 FLORES+ 基准以纳入低资源语言 Emakhuwa，通过葡萄牙语翻译并经质量检查构建了多参考数据集，基线实验表明拼写不一致导致模型表现不佳，强调了进一步研究的必要性。
摘要：
作为 Open Language Data Initiative 共享任务的一部分，我们扩展了 FLORES+ 评估集以纳入 Emakhuwa，一种在莫桑比克广泛使用的低资源语言。我们将 dev 和 devtest 集从葡萄牙语翻译成 Emakhuwa，并详细说明了翻译过程和所用的质量保证措施。我们的方法涉及多项质量检查，包括后编辑和充分性评估。生成的数据集为每个源句子包含多个参考句子。我们展示了训练 Neural Machine Translation 系统和微调现有 multilingual translation models 的基线结果。我们的发现表明，拼写不一致在 Emakhuwa 中仍是一个挑战。此外，基线模型在该评估集上表现不佳，凸显了进一步研究以提升 Emakhuwa 机器翻译质量的必要性。数据可在 https://huggingface.co/datasets/LIACC/Emakhuwa-FLORES 公开获取。
英文摘要：
As part of the Open Language Data Initiative shared tasks, we have expanded the FLORES+ evaluation set to include Emakhuwa, a low-resource language widely spoken in Mozambique. We translated the dev and devtest sets from Portuguese into Emakhuwa, and we detail the translation process and quality assurance measures used. Our methodology involved various quality checks, including post-editing and adequacy assessments. The resulting datasets consist of multiple reference sentences for each source. We present baseline results from training a Neural Machine Translation system and fine-tuning existing multilingual translation models. Our findings suggest that spelling inconsistencies remain a challenge in Emakhuwa. Additionally, the baseline models underperformed on this evaluation set, underscoring the necessity for further research to enhance machine translation quality for Emakhuwa. The data is publicly available at https://huggingface.co/datasets/LIACC/Emakhuwa-FLORES.
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。
