Learning to Predict Distributions of Words Across Domains

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 partof-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 stateof-the-art methods, while requiring no task-specific customisations.