论文信息 - Comparing the Accuracy of CCG and Penn Treebank Parsers

Comparing the Accuracy of CCG and Penn Treebank Parsers

We compare the CCG parser of Clark and Curran (2007) with a state-of-the-art Penn Treebank (PTB) parser. An accuracy comparison is performed by converting the CCG derivations into PTB trees. We show that the conversion is extremely difficult to perform, but are able to fairly compare the parsers on a representative subset of the PTB test section, obtaining results for the CCG parser that are statistically no different to those for the Berkeley parser.

James R. Curran | Stephen Clark

[1] Ted Briscoe,et al. Evaluating the Accuracy of an Unlexicalized Statistical Parser on the PARC DepBank , 2006, ACL.

[2] Dan Klein,et al. Improved Inference for Unlexicalized Parsing , 2007, NAACL.

[3] Jun'ichi Tsujii,et al. Comparative Parser Performance Analysis across Grammar Frameworks through Automatic Tree Conversion using Synchronous Grammars , 2008, COLING.

[4] Mark Steedman,et al. CCGbank: A Corpus of CCG Derivations and Dependency Structures Extracted from the Penn Treebank , 2007, CL.

[5] James R. Curran,et al. Wide-Coverage Efficient Statistical Parsing with CCG and Log-Linear Models , 2007, Computational Linguistics.

[6] Michael Collins,et al. Head-Driven Statistical Models for Natural Language Parsing , 2003, CL.

[7] Jun'ichi Tsujii,et al. Probabilistic Disambiguation Models for Wide-Coverage HPSG Parsing , 2005, ACL.

[8] Mark Johnson,et al. Parsing the Wall Street Journal using a Lexical-Functional Grammar and Discriminative Estimation Techniques , 2002, ACL.