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.

• Type: Journal
• Year: 2009
• Where: ACL
• Authors: Stephen Clark, James R. Curran
• Keywords: ACL 2009, CCG Parser, Computational Linguistics, Parser, PTB Test Section