Paper: Simpler unsupervised POS tagging with bilingual projections

ACL ID P13-2112
Title Simpler unsupervised POS tagging with bilingual projections
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

We present an unsupervised approach to part-of-speech tagging based on projec- tions of tags in a word-aligned bilingual parallel corpus. In contrast to the exist- ing state-of-the-art approach of Das and Petrov, we have developed a substantially simpler method by automatically identi- fying ?good? training sentences from the parallel corpus and applying self-training. In experimental results on eight languages, our method achieves state-of-the-art re- sults. 1 Unsupervised part-of-speech tagging Currently, part-of-speech (POS) taggers are avail- able for many highly spoken and well-resourced languages such as English, French, German, Ital- ian, and Arabic. For example, Petrov et al. (2012) build supervised POS taggers for 22 languages us- ing the TNT tagger (Brants, 2000), with an aver- a...