Sciweavers

JMLR
2011
105views more  JMLR 2011»
13 years 6 months ago
Posterior Sparsity in Unsupervised Dependency Parsing
A strong inductive bias is essential in unsupervised grammar induction. In this paper, we explore a particular sparsity bias in dependency grammars that encourages a small number ...
Jennifer Gillenwater, Kuzman Ganchev, João ...
CORR
2011
Springer
145views Education» more  CORR 2011»
13 years 6 months ago
A Universal Part-of-Speech Tagset
To facilitate future research in unsupervised induction of syntactic structure and to standardize best-practices, we propose a tagset that consists of twelve universal part-ofspee...
Slav Petrov, Dipanjan Das, Ryan McDonald
NAACL
2010
13 years 9 months ago
From Baby Steps to Leapfrog: How "Less is More" in Unsupervised Dependency Parsing
We present three approaches for unsupervised grammar induction that are sensitive to data complexity and apply them to Klein and Manning's Dependency Model with Valence. The ...
Valentin I. Spitkovsky, Hiyan Alshawi, Daniel Jura...
EMNLP
2010
13 years 9 months ago
Improved Fully Unsupervised Parsing with Zoomed Learning
We introduce a novel training algorithm for unsupervised grammar induction, called Zoomed Learning. Given a training set T and a test set S, the goal of our algorithm is to identi...
Roi Reichart, Ari Rappoport
ACL
2010
13 years 9 months ago
Sparsity in Dependency Grammar Induction
A strong inductive bias is essential in unsupervised grammar induction. We explore a particular sparsity bias in dependency grammars that encourages a small number of unique depen...
Jennifer Gillenwater, Kuzman Ganchev, João ...
CEC
2010
IEEE
14 years 16 days ago
Evolving natural language grammars without supervision
Unsupervised grammar induction is one of the most difficult works of language processing. Its goal is to extract a grammar representing the language structure using texts without a...
Lourdes Araujo, Jesus Santamaria
ACL
2006
14 years 25 days ago
Prototype-Driven Grammar Induction
We investigate prototype-driven learning for primarily unsupervised grammar induction. Prior knowledge is specified declaratively, by providing a few canonical examples of each ta...
Aria Haghighi, Dan Klein