Interactive optimization of embedding-based text similarity calculations

Comparing text documents is an essential task for a variety of applications within diverse research fields, and several different methods have been developed this. However, calculating similarity ambiguous context-dependent task, so many open challenges still exist. In this paper, we present novel method calculations based on the combination embedding technology ensemble methods. By using embeddings, instead only one, show that it possible to achieve higher quality, which in turn key factor developing high-performing exploitation. We also provide prototype visual analytics tool helps analyst find optimal performing ensembles gain insights inner workings calculations. Furthermore, discuss generalizability our ideas fields beyond scope analysis.