English

Unsupervised Cross-Domain Word Representation Learning

Computation and Language 2015-05-28 v1

Abstract

Meaning of a word varies from one domain to another. Despite this important domain dependence in word semantics, existing word representation learning methods are bound to a single domain. Given a pair of \emph{source}-\emph{target} domains, we propose an unsupervised method for learning domain-specific word representations that accurately capture the domain-specific aspects of word semantics. First, we select a subset of frequent words that occur in both domains as \emph{pivots}. Next, we optimize an objective function that enforces two constraints: (a) for both source and target domain documents, pivots that appear in a document must accurately predict the co-occurring non-pivots, and (b) word representations learnt for pivots must be similar in the two domains. Moreover, we propose a method to perform domain adaptation using the learnt word representations. Our proposed method significantly outperforms competitive baselines including the state-of-the-art domain-insensitive word representations, and reports best sentiment classification accuracies for all domain-pairs in a benchmark dataset.

Keywords

Cite

@article{arxiv.1505.07184,
  title  = {Unsupervised Cross-Domain Word Representation Learning},
  author = {Danushka Bollegala and Takanori Maehara and Ken-ichi Kawarabayashi},
  journal= {arXiv preprint arXiv:1505.07184},
  year   = {2015}
}

Comments

53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conferences on Natural Language Processing of the Asian Federation of Natural Language Processing

R2 v1 2026-06-22T09:42:04.778Z