Downsampling Strategies are Crucial for Word Embedding Reliability

08/21/2018

∙

by   Johannes Hellrich, et al.

∙

0

∙

share

The reliability of word embeddings algorithms, i.e., their ability to provide consistent computational judgments of word similarity when trained repeatedly on the same data set, has recently raised concerns. We compared the effect of probabilistic and weighting as downsampling strategies. We found the latter to provide superior reliability while being competitive in accuracy when applied to singular value decomposition-based embeddings