Task-specific Word-Clustering for Part-of-Speech Tagging

While the use of cluster features became ubiquitous in core NLP tasks, most cluster features in NLP are based on distributional similarity. We propose a new type of clustering criteria, specific to the task of part-of-speech tagging. Instead of distributional similarity, these clusters are based on the beha vior of a baseline tagger when applied to a large corpus. These cluster features provide similar gains in accuracy to those achieved by distributional-similarity derived clusters. Using both types of cluster features together further improve tagging accuracies. We show that the method is effective for both the in-domain and out-of-domain scenarios for English, and for French, German and Italian. The effect is larger for out-of-domain text.