Authors
Douwe Kiela, Felix Hill, Stephen Clark
Publication date
2015
Conference
Proceedings of the Empirical Methods in Natural Language Processing Conference
Publisher
Association for Computational Linguistics
Description
We demonstrate the advantage of specializing semantic word embeddings for either similarity or relatedness. We compare two variants of retrofitting and a joint-learning approach, and find that all three yield specialized semantic spaces that capture human intuitions regarding similarity and relatedness better than unspecialized spaces. We also show that using specialized spaces in NLP tasks and applications leads to clear improvements, for document classification and synonym selection, which rely on either similarity or relatedness but not both.
Scholar articles
D Kiela, F Hill, S Clark - Proceedings of the 2015 conference on empirical …, 2015