Tailoring Word Embeddings for Bilexical Predictions: An Experimental Comparison

12/22/2014

∙

by   Pranava Swaroop Madhyastha, et al.

∙

0

∙

share

We investigate the problem of inducing word embeddings that are tailored for a particular bilexical relation. Our learning algorithm takes an existing lexical vector space and compresses it such that the resulting word embeddings are good predictors for a target bilexical relation. In experiments we show that task-specific embeddings can benefit both the quality and efficiency in lexical prediction tasks.