Cross-Lingual Discriminative Learning of Sequence Models with Posterior Regularization

We present a framework for cross-lingual transfer of sequence information from a resource-rich source language to a resourceimpoverished 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 random field model on the target side.Our posterior 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 namedentity segmentation.