Task-specific Word-Clustering for Part-of-Speech Tagging
This is an incremental improvement for NLP practitioners working on part-of-speech tagging, particularly in cross-lingual and out-of-domain scenarios.
The paper tackled the problem of part-of-speech tagging by proposing task-specific word-clustering based on baseline tagger behavior, which improved tagging accuracies similarly to distributional-similarity clusters, with larger gains for out-of-domain text across multiple languages.
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.