Tailoring Word Embeddings for Bilexical Predictions: An Experimental Comparison
This work addresses the need for more efficient and accurate lexical predictions in natural language processing, but it is incremental as it builds on existing embedding methods.
The authors tackled the problem of creating word embeddings optimized for specific bilexical relations by compressing existing lexical vector spaces, resulting in improved quality and efficiency in lexical prediction tasks.
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.