Paper: Biased Representation Learning for Domain Adaptation

ACL ID D12-1120
Title Biased Representation Learning for Domain Adaptation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2012
Authors

Representation learning is a promising tech- nique for discovering features that allow su- pervised classifiers to generalize from a source domain dataset to arbitrary new domains. We present a novel, formal statement of the rep- resentation learning task. We argue that be- cause the task is computationally intractable in general, it is important for a representa- tion learner to be able to incorporate expert knowledge during its search for helpful fea- tures. Leveraging the Posterior Regularization framework, we develop an architecture for in- corporating biases into representation learn- ing. We investigate three types of biases, and experiments on two domain adaptation tasks show that our biased learners identify signif- icantly better sets of features than unbiased learners, resulting ...