Unsupervised Structure Prediction with Non-Parallel Multilingual Guidance

Unsupervised Structure Prediction with Non-Parallel Multilingual Guidance

Cached

Download Links

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

Citations:

BibTeX

@MISC{Cohen_unsupervisedstructure,
    author = {Shay B. Cohen and Dipanjan Das and Noah A. Smith},
    title = {Unsupervised Structure Prediction with Non-Parallel Multilingual Guidance},
    year = {}
}

Bookmark

OpenURL

Abstract

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. 1

Citations

312	On the limited memory BFGS method for large scale optimization - Liu, Nocedal - 1989
212	Tagging English text with probabilistic model - Merialdo - 1994
161	CoNLL-X shared task on multilingual dependency parsing - Buchholz, Marsi - 2006
128	Corpusbased induction of syntactic structure: Models of dependency and constituency - Klein, Manning - 2004
114	Building a Syntactically Annotated Corpus: The Prague Dependency Treebank - Hajič - 1998
94	The CoNLL 2007 shared task on dependency parsing - Nivre, Hall, et al. - 2007
89	Contrastive Estimation: Training Log-Linear Models on Unlabeled Data - Smith, Eisner - 2005
86	Does Baum-Welch re-estimation help taggers - Elworthy - 1994
42	Bilingual parsing with factored estimation: Using English to parse Korean - Smith, Smith - 2004
39	Posterior regularization for structured latent variable models - Ganchev, Graça, et al. - 2010
37	Shared logistic normal distributions for soft parameter tying in unsupervised grammar induction - Cohen, Smith - 2009
33	Painless unsupervised learning with features - Berg-Kirkpatrick, Bouchard-Côté, et al. - 2010
29	Two languages are better than one (for syntactic parsing - Burkett, Klein - 2008
28	Bayesian inference for PCFGs via Markov chain Monte Carlo - Johnson, Griffiths, et al. - 2007
26	Fast unsupervised incremental parsing - Seginer - 2007
25	Unsupervised multilingual learning for morphological segmentation - Snyder, Barzilay - 2008
24	Improving unsupervised dependency parsing with richer contexts and smoothing - Headden, Johnson, et al. - 2009
22	Building the Italian Syntactic-Semantic Treebank - Montemagni, Barsotti, et al. - 2003
20	Novel Estimation Methods for Unsupervised Discovery of Latent Structure in Natural Language Text - Smith - 2006
19	Using Universal Linguistic Knowledge to Guide Grammar Induction - Naseem, Chen, et al. - 2010
19	From baby steps to leapfrog: How “less is more” in unsupervised dependency parsing - Spitkovsky, Alshawi, et al. - 2010
15	Phylogenetic Grammar Induction - Berg-Kirkpatrick, Klein - 2010
12	Joint morphological and syntactic disambiguation - Cohen, Smith - 2007
12	Unsupervised Partof-Speech Tagging with Bilingual Graph-Based Projections - Das, Petrov - 2011
10	Multi-Source Transfer of Delexicalized Dependency Parsers - McDonald, Petrov, et al. - 2011
10	Multilingual part-of-speech tagging: Two unsupervised approaches - Naseem, Snyder, et al. - 2009
10	Parser adaptation and projection with quasisynchronous grammar features - Smith, Eisner - 2009
9	Sparsity in dependency grammar induction - Gillenwater, Ganchev, et al. - 2010
4	N.A.: Covariance in unsupervised learning of probabilistic grammars - Cohen, Smith - 2010
3	A universal part-of-speech tagset. Arxiv preprint ArXiv:1104.2086 - Petrov, Das, et al. - 2011
3	Unsupervised multilingual grammar induction - Snyder, Naseem, et al. - 2009
1	Prototype driven learning for sequence models - Haghighi, Klein - 2006