Embeddings models for Buddhist Sanskrit: Evaluation Datasets

<p>Evaluation Dataset used for the study published as&nbsp;&nbsp;Embeddings models for Buddhist Sanskrit,&nbsp; <em>LREC 2022 proceedings</em>. It contains a semantic similarity dataset&nbsp;and an analogy dataset, as well as the published study and a ReadMe file containing the&nbsp;guidelines used for scoring semantic &nbsp;similarity and some notes about the manual scoring task.</p> <p>&nbsp;</p> <p>The evaluation datasets have been prepared by&nbsp;Ligeia Lugli,&nbsp; Bruno Galasek-Hul, Luis Qui&ntilde;ones and Jai Paranjape</p> <p>&nbsp;</p>