Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning
E Vylomova, L Rimell, T Cohn, T Baldwin
PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1 | The Association for Computational Linguistics | Published : 2016
Recent work has shown that simple vector subtraction over word embeddings is surprisingly effective at capturing different lexical relations, despite lacking explicit supervision. Prior work has evaluated this intriguing result using a word analogy prediction formulation and hand-selected relations, but the generality of the finding over a broader range of lexical relation types and different learning settings has not been evaluated. In this paper, we carry out such an evaluation in two learning settings: (1) spectral clustering to induce word relations, and (2) supervised learning to classify vector differences into relation types. We find that word embeddings capture a surprising amount of..View full abstract
Awarded by EPSRC
Awarded by ERC
LR was supported by EPSRC grant EP/1037512/1 and ERC Starting Grant DisCoTex (306920). TC and TB were supported by the Australian Research Council.