Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

8

NAACL
2007

favoriteEmaildiscussreport

116views Computational Linguistics» more NAACL 2007»

Tree Revision Learning for Dependency Parsing

13 years 6 months ago

Tree Revision Learning for Dependency Parsing

Download www.aclweb.org

We present a revision learning model for improving the accuracy of a dependency parser. The revision stage corrects the output of the base parser by means of revision rules learned from the mistakes of the base parser itself. Revision learning is performed with a discriminative classiﬁer. The revision stage has linear complexity and preserves the efﬁciency of the base parser. We present empirical evaluations on the treebanks of two languages, which show effectiveness in relative error reduction and state of the art accuracy.

Giuseppe Attardi, Massimiliano Ciaramita

Real-time Traffic

Base Parser | Computational Linguistics | NAACL 2007 | Revision Learning | Revision Stage |

claim paper

Related Content

» Multilingual Dependency Parsing and Domain Adaptation using DeSR

» Probabilistic Models for ActionBased Chinese Dependency Parsing

» Online Learning for Deterministic Dependency Parsing

» Online Learning of Approximate Dependency Parsing Algorithms

» Efficient Convolution Kernels for Dependency and Constituent Syntactic Trees

» A Comparison of Alternative Parse Tree Paths for Labeling Semantic Roles

» Unsupervised Induction of Tree Substitution Grammars for Dependency Parsing

» Bitext Dependency Parsing with Bilingual Subtree Constraints

» Detecting and Parsing Architecture at City Scale from Range Data

Post Info
More Details (n/a)

Added	30 Oct 2010
Updated	30 Oct 2010
Type	Conference
Year	2007
Where	NAACL
Authors	Giuseppe Attardi, Massimiliano Ciaramita

Comments (0)