Adding More Languages Improves Unsupervised Multilingual Part-of-Speech Tagging: A Bayesian Non-Parametric Approach

Abstract

We investigate the problem of unsupervised part-of-speech tagging when raw parallel data is available in a large number of languages. Patterns of ambiguity vary greatly across languages and therefore even unannotated multilingual data can serve as a learning signal. We propose a non-parametric Bayesian model that connects related tagging decisions across languages through the use of multilingual latent variables. Our experiments show that performance improves steadily as the number of languages increases.