Unsupervised Structure Prediction with Non-Parallel Multilingual Guidance

Shay B. Cohen, Dipanjan Das, Noah A. Smith

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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-the-art performance for two tasks of structure prediction: unsupervised part-of-speech tagging and unsupervised dependency parsing.
Original languageEnglish
Title of host publicationProceedings of the 2011 Conference on Empirical Methods in Natural Language Processing
Place of PublicationEdinburgh, Scotland, UK.
PublisherAssociation for Computational Linguistics
Number of pages12
Publication statusPublished - 1 Jul 2011


Dive into the research topics of 'Unsupervised Structure Prediction with Non-Parallel Multilingual Guidance'. Together they form a unique fingerprint.

Cite this