Paper: Zipfian corruptions for robust POS tagging

ACL ID N13-1077
Title Zipfian corruptions for robust POS tagging
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Main Conference
Year 2013

Inspired by robust generalization and adver- sarial learning we describe a novel approach to learning structured perceptrons for part-of- speech (POS) tagging that is less sensitive to domain shifts. The objective of our method is to minimize average loss under random distri- bution shifts. We restrict the possible target distributions to mixtures of the source distri- bution and random Zipfian distributions. Our algorithm is used for POS tagging and eval- uated on the English Web Treebank and the Danish Dependency Treebank with an average 4.4% error reduction in tagging accuracy.