Unsupervised Dependency Parsing with Transferring Distribution via Parallel Guidance and Entropy Regularization

We present a novel approach for inducing unsupervised dependency parsers for languages that have no labeled training data, but have translated text in a resourcerich language. We train probabilistic parsing models for resource-poor languages by transferring cross-lingual knowledge from resource-rich language with entropy regularization. Our method can be used as a purely monolingual dependency parser, requiring no human translations for the test data, thus making it applicable to a wide range of resource-poor languages. We perform experiments on three Data sets — Version 1.0 and version 2.0 of Google Universal Dependency Treebanks and Treebanks from CoNLL shared-tasks, across ten languages. We obtain stateof-the art performance of all the three data sets when compared with previously studied unsupervised and projected parsing systems.