Paper: Domain Adaptation With Structural Correspondence Learning

ACL ID W06-1615
Title Domain Adaptation With Structural Correspondence Learning
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2006

Discriminative learning methods are widely used in natural language process- ing. These methods work best when their training and test data are drawn from the same distribution. For many NLP tasks, however, we are confronted with new domains in which labeled data is scarce or non-existent. In such cases, we seek to adapt existing models from a resource- rich source domain to a resource-poor target domain. We introduce structural correspondence learning to automatically induce correspondences among features from different domains. We test our tech- nique on part of speech tagging and show performance gains for varying amounts of source and target training data, as well as improvements in target domain parsing accuracy using our improved tagger.