Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning
Loading...
Citations
Scopus:
Altmetric:
Altmetric::
Download
Associated Records
Authors
File Licence
Date
2016
Source Title
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics
Journal Title
Journal ISSN
Volume Title
Publisher
The Association for Computational Linguistics
Melbourne Authors
Affiliation
Computing and Information Systems
Document Type
Conference Paper
Subject Code
Citation
Vylomova, E., Rimell, L., Cohn, T. & Baldwin, T. (2016). Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning. Erk, K (Ed.) Smith, NA (Ed.) Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 3, pp.1671-1682. The Association for Computational Linguistics. https://doi.org/10.18653/v1/p16-1158.
Access Status
Open Access
Access URL
Open Access URL
Open Access at PMC
Linked Resource URL
NHMRC Grant Code
ARC Grant Code
Description
Abstract
Recent work on word embeddings has shown that simple vector subtraction over
pre-trained 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 information, and that, under suitable supervised training,
vector subtraction generalises well to a broad range of relations, including
over unseen lexical items.