mteb/NovelQA

NovelQA是一个基于LMEB（长时记忆嵌入基准）的语义检索任务数据集，专注于从长篇小说中检索与角色、情节、背景、关系和时序问题相关的段落。该数据集用于评估文本嵌入模型在小说领域的检索性能，属于MTEB（大规模文本嵌入基准）的一部分，任务类别为文本到文本检索，领域涵盖小说和书面文本。NovelQA is an LMEB semantic retrieval task based on NovelQA, retrieving passages from long-form fiction for character, plot, setting, relation, and temporal questions. It is part of the MTEB (Massive Text Embedding Benchmark) for evaluating embedding models in the fiction domain, with a task category of text-to-text retrieval and domains including fiction and written text.