Carnegie Mellon University
file.pdf (228.64 kB)
Download file

Unsupervised Structure Prediction with Non-Parallel Multilingual Guidance

Download (228.64 kB)
journal contribution
posted on 2011-07-01, 00:00 authored by Shay B. Cohen, Dipanjan Das, Noah A. Smith

We describe a method for prediction of linguistic structure in a language for which only unlabeled data is available, using annotated data from a set of one or more helper languages. Our approach is based on a model that locally mixes between supervised models from the helper languages. Parallel data is not used, allowing the technique to be applied even in domains where human-translated texts are unavailable. We obtain state-of-theart performance for two tasks of structure prediction: unsupervised part-of-speech tagging and unsupervised dependency parsing.


Publisher Statement

Copyright 2011 ACL



Usage metrics