aisingapore/nlg-machine_translation
收藏Hugging Face2024-12-20 更新2024-12-21 收录
下载链接：
https://hf-mirror.com/datasets/aisingapore/nlg-machine_translation
下载链接
链接失效反馈官方服务：
资源简介：
SEA Machine Translation数据集用于评估模型将文档从源语言翻译成目标语言的连贯性和流畅性。该数据集包含多种语言对，如英语到印尼语、英语到高棉语、英语到缅甸语等，并且提供了fewshot示例。数据集来源于FLORES 200和NusaX数据集，许可证为CC BY-SA 4.0。
The SEA Machine Translation dataset is designed to evaluate a models ability to translate documents from a source language to a target language coherently and fluently. It is sampled from FLORES 200 and NusaX, covering languages such as Burmese, Chinese, English, Indonesian, Javanese, Khmer, Malay, Sundanese, Tamil, Thai, and Vietnamese. The dataset is split into various language pairs with additional fewshot examples. Its purpose is to evaluate chat or instruction-tuned large language models (LLMs) and is part of the SEA-HELM leaderboard from AI Singapore.
提供机构：
aisingapore
