masakhane/AfriMTE-WMT2024

AfriMTE-WMT2024数据集是用于WMT 2024 Metrics Shared Task的挑战集，旨在评估13种非洲语言对的机器翻译质量。该数据集支持非洲机器翻译评估和质量估计的研究与开发。每个样本包含源句(source)、机器翻译输出(hypothesis)、人工参考翻译(reference)、质量评分(score)等信息。数据集共包含2,815个样本，涵盖13种语言对，如英语-斯瓦希里语(eng-swh)、英语-豪萨语(eng-hau)、约鲁巴语-英语(yor-eng)等。该数据集仅作为测试集使用，没有训练数据，主要用于评估目的。

The AfriMTE-WMT2024 dataset is a challenge set used in the WMT 2024 Metrics Shared Task for evaluating machine translation quality across 13 African-centric language pairs. This dataset aims to support research and development in African machine translation evaluation and quality estimation. Each example contains source sentence, machine translation output, human reference translation, quality score, and language pair information. The dataset contains 2,815 samples across 13 language pairs including English-Swahili (eng-swh), English-Hausa (eng-hau), Yoruba-English (yor-eng), etc. The dataset is test-only (no training data) and is designed for evaluation purposes.