Counter-fitting Word Vectors to Linguistic Constraints
Computation and Language
2016-03-04 v1 Machine Learning
Abstract
In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic similarity. Applying this method to publicly available pre-trained word vectors leads to a new state of the art performance on the SimLex-999 dataset. We also show how the method can be used to tailor the word vector space for the downstream task of dialogue state tracking, resulting in robust improvements across different dialogue domains.
Cite
@article{arxiv.1603.00892,
title = {Counter-fitting Word Vectors to Linguistic Constraints},
author = {Nikola Mrkšić and Diarmuid Ó Séaghdha and Blaise Thomson and Milica Gašić and Lina Rojas-Barahona and Pei-Hao Su and David Vandyke and Tsung-Hsien Wen and Steve Young},
journal= {arXiv preprint arXiv:1603.00892},
year = {2016}
}
Comments
Paper accepted for the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2016)