MNLI(Multi-Genre Natural Language Inference)是一个大规模的自然语言推理数据集,包含433,000多对句子对。该数据集用于评估模型在不同文本类型中的推理能力,包括新闻文章、小说、论坛帖子等。每个句子对都标注了三种可能的关系:蕴含(entailment)、矛盾(contradiction)和中性(neutral)。
This dataset is a port of the official mnli dataset on the Hub. It contains the matched version. Note that the premise and hypothesis columns have been renamed to text1 and text2 respectively. Also, t