Paper: Online EM for Unsupervised Models

ACL ID N09-1069
Title Online EM for Unsupervised Models
Venue Human Language Technologies
Session Main Conference
Year 2009

The (batch) EM algorithm plays an important role in unsupervised induction, but it some- times suffers from slow convergence. In this paper, we show that online variants (1) provide significant speedups and (2) can even find bet- ter solutions than those found by batch EM. We support these findings on four unsuper- vised tasks: part-of-speech tagging, document classification, word segmentation, and word alignment.