Learning to predict distributions of words across domains

Bollegala, Danushka, Weir, David and Carroll, John (2014) Learning to predict distributions of words across domains. In: 52nd Annual Meeting of the Association for Computational Linguistics, 23-25 Jun 2014, Baltimore, MD.

[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 or Workshop Item (Paper)
Schools and Departments: School of Engineering and Informatics > Informatics
Subjects: Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Depositing User: John Carroll
Date Deposited: 23 Apr 2015 15:39
Last Modified: 23 Apr 2015 15:39
URI: http://sro.sussex.ac.uk/id/eprint/53735

View download statistics for this item

📧 Request an update