Sciweavers

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

8

EMNLP
2007

favoriteEmaildiscussreport

93views Natural Language Processing» more EMNLP 2007»

Characterizing the Errors of Data-Driven Dependency Parsing Models

13 years 6 months ago

Characterizing the Errors of Data-Driven Dependency Parsing Models

Download acl.ldc.upenn.edu

We present a comparative error analysis of the two dominant approaches in datadriven dependency parsing: global, exhaustive, graph-based models, and local, greedy, transition-based models. We show that, in spite of similar performance overall, the two models produce different types of errors, in a way that can be explained by theoretical properties of the two models. This analysis leads to new directions for parser development.

Ryan T. McDonald, Joakim Nivre

Real-time Traffic

Comparative Error Analysis | EMNLP 2007 | Graph-based Models | Natural Language Processing | Transition-based Models |

claim paper

Related Content

» Graph Transformations in DataDriven Dependency Parsing

» Integrating GraphBased and TransitionBased Dependency Parsers

» Extracting Narrative Timelines as Temporal Dependency Structures

» Critical Charge Characterization for Soft Error Rate Modeling in 90nm SRAM

» Sentence diagram generation using dependency parsing

» A Pipeline Framework for Dependency Parsing

» Tree Revision Learning for Dependency Parsing

» Unlexicalised Hidden Variable Models of Split Dependency Grammars

» Coordinate Noun Phrase Disambiguation in a Generative Parsing Model

Post Info
More Details (n/a)

Added	29 Oct 2010
Updated	29 Oct 2010
Type	Conference
Year	2007
Where	EMNLP
Authors	Ryan T. McDonald, Joakim Nivre

Comments (0)