Learning to predict distributions of words across domains

Bollegala, Danushka, Weir, David and Carroll, John (2014) Learning to predict distributions of words across domains. 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, Maryland, USA, 23-25 June 2014. Published in: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 613-623. The Association for Computational Linguistics ISBN 9781937284725

[img]
Preview
PDF - Published Version
Download (262kB) | Preview

Abstract

Although the distributional hypothesis has been applied successfully in many natural language processing tasks, systems using distributional information have been limited to a single domain because the distribution of a word can vary between domains as the word’s predominant meaning changes. However, if it were possible to predict how the distribution of a word changes from one domain to another, the predictions could be used to adapt a system trained in one domain to work in another. We propose an unsupervised method to predict the distribution of a word in one domain, given its distribution in another domain. We evaluate our method on two tasks: cross-domain part-of-speech tagging and cross-domain sentiment classification. In both tasks, our method significantly outperforms competitive baselines and returns results that are statistically comparable to current state-of-the-art methods, while requiring no task-specific customisations.

Item Type: Conference Proceedings
Schools and Departments: School of Engineering and Informatics > Informatics
Subjects: Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Related URLs:
Depositing User: John Carroll
Date Deposited: 23 Apr 2015 15:39
Last Modified: 19 Jun 2018 14:27
URI: http://sro.sussex.ac.uk/id/eprint/53735

View download statistics for this item

📧 Request an update