Difference between revisions of "Headden et al. NAACL 09"

From Cohen Courses
Jump to navigationJump to search
m
m
Line 7: Line 7:
 
This paper improves on unsupervised [[AddressesProblem::dependency parsing]] by introducing basic valence frames and lexical information. Smoothing is also performed to leverage on this additional information. Their model produces 10 percentage points improvements over previous work in unsupervised (dependency) grammar induction.
 
This paper improves on unsupervised [[AddressesProblem::dependency parsing]] by introducing basic valence frames and lexical information. Smoothing is also performed to leverage on this additional information. Their model produces 10 percentage points improvements over previous work in unsupervised (dependency) grammar induction.
  
The paper builds upon the [[RelatedPaper::Dependency Model with Valence]] model by Klein and Manning (2004) [[RelatedPaper::http://www.cs.berkeley.edu/~klein/papers/acl04-factored_induction.pdf | haha]].
+
The paper builds upon the [[RelatedPaper::Dependency Model with Valence]] by Klein and Manning (2004).
  
 
== Brief description of the method ==
 
== Brief description of the method ==
Line 15: Line 15:
  
 
== Related Papers ==
 
== Related Papers ==
 +
 +
[http://www.cs.berkeley.edu/~klein/papers/acl04-factored_induction.pdf Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency]. D Klein and C Manning (2004). In ''ACL 2004''

Revision as of 18:08, 29 November 2011

Improving Unsupervised Dependency Parsing with Richer Contexts and Smoothing, by W. P. Headden III, W Headden III, M Johnson, D McClosky. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2009.

This Paper is available online [1].

Summary

This paper improves on unsupervised dependency parsing by introducing basic valence frames and lexical information. Smoothing is also performed to leverage on this additional information. Their model produces 10 percentage points improvements over previous work in unsupervised (dependency) grammar induction.

The paper builds upon the Dependency Model with Valence by Klein and Manning (2004).

Brief description of the method

Experimental Result

Related Papers

Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency. D Klein and C Manning (2004). In ACL 2004