Learning task-specific bilexical embeddings

View/Open
Document typeConference report
Defense date2014
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial
property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public
communication or transformation of this work are prohibited without permission of the copyright holder
Abstract
We present a method that learns bilexical operators over distributional representations of words and leverages supervised data for a linguistic relation. The learning algorithm exploits lowrank bilinear forms and induces low-dimensional embeddings of the lexical space tailored for the target linguistic relation. An advantage of imposing low-rank constraints is that prediction
is expressed as the inner-product between low-dimensional embeddings, which can have great computational benefits. In experiments with multiple linguistic bilexical relations we show that our method effectively learns using embeddings of a few dimensions.
CitationMadhyastha, P.S.; Carreras, X.; Quattoni, A. Learning task-specific bilexical embeddings. A: International Conference on Computational Linguistics. "Proceedings of the 25th International Conference on Computational Linguistics". Dublin: 2014, p. 161-171.
ISBN978-1-941643-26-6 ii
Publisher versionhttp://anthology.aclweb.org/C/C14/C14-1017.pdf
Collections
Files | Description | Size | Format | View |
---|---|---|---|---|
Pranava et al.pdf | 211,9Kb | View/Open |