Paper: Cross-Lingual Discriminative Learning of Sequence Models with Posterior Regularization

ACL ID D13-1205
Title Cross-Lingual Discriminative Learning of Sequence Models with Posterior Regularization
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2013
Authors

We present a framework for cross-lingual transfer of sequence information from a resource-rich source language to a resource- impoverished target language that incorporates soft constraints via posterior regularization. To this end, we use automatically word aligned bitext between the source and target language pair, and learn a discriminative conditional ran- dom field model on the target side. Our poste- rior regularization constraints are derived from simple intuitions about the task at hand and from cross-lingual alignment information. We show improvements over strong baselines for two tasks: part-of-speech tagging and named- entity segmentation.