ChineseSimilarityDataSets

This dataset contains benchmark similarity results for large-scale Chinese long-text similarity analysis across lexical, semantic, and hybrid paradigms. The corpus consists of <b>45 Chinese texts</b> spanning <b>modern literature, Ming–Qing dynasty novels, modern essays, and ancient Chinese essays</b>.For each text, three length variants are provided: <b>long (100%)</b>, <b>medium (50%)</b>, and <b>short (20%)</b>, forming a total of <b>nine experimental subsets</b>. Ground-truth relations are hierarchically defined at four levels: <b>same chapter, same book, same author, and same category</b>.