Exploiting Reducibility in Unsupervised Dependency Parsing

The possibility of deleting a word from a sentence without violating its syntactic correctness belongs to traditionally known manifestations of syntactic dependency. We introduce a novel unsupervised parsing approach that is based on a new n-gram reducibility measure. We perform experiments across 18 languages available in CoNLL data and we show that our approach achieves better accuracy for the majority of the languages then previously reported results.

[1]  Ben Taskar,et al.  Posterior Sparsity in Unsupervised Dependency Parsing , 2011, J. Mach. Learn. Res..

[2]  Valentin I. Spitkovsky,et al.  Lateen EM: Unsupervised Training with Multiple Objectives, Applied to Dependency Grammar Induction , 2011, EMNLP.

[3]  Sabine Buchholz,et al.  CoNLL-X Shared Task on Multilingual Dependency Parsing , 2006, CoNLL.

[4]  Valentin I. Spitkovsky,et al.  Punctuation: Making a Point in Unsupervised Dependency Parsing , 2011, CoNLL.

[5]  Sylvain Kahane,et al.  Defining dependencies (and constituents) , 2011, DepLing.

[6]  Valentin I. Spitkovsky,et al.  Unsupervised Dependency Parsing without Gold Part-of-Speech Tags , 2011, EMNLP.

[7]  Mark Johnson,et al.  Improving Unsupervised Dependency Parsing with Richer Contexts and Smoothing , 2009, NAACL.

[8]  Noah A. Smith,et al.  Logistic Normal Priors for Unsupervised Probabilistic Grammar Induction , 2008, NIPS.

[9]  Jason Eisner,et al.  Three New Probabilistic Models for Dependency Parsing: An Exploration , 1996, COLING.

[10]  Noah A. Smith,et al.  Novel estimation methods for unsupervised discovery of latent structure in natural language text , 2007 .

[11]  Jirí Havelka.  Beyond Projectivity: Multilingual Evaluation of Constraints and Measures on Non-Projective Structures , 2007, ACL.

[12]  Martin Plátek,et al.  Modeling Syntax of Free Word-Order Languages: Dependency Analysis by Reduction , 2005, TSD.

[13]  Zdenek Zabokrtský,et al.  Language Richness of the Web , 2012, LREC.