D08-1050 categories in the set used by the CCG parser . Supertagging was originally
D08-1050 behaviours with regard to porting the CCG parser . 2 The CCG Parser The CCG parser
D09-1085 Clark et al. ( 2004 ) evaluated a CCG parser on a small corpus of object extraction
C04-1041 speeds we have reported for the CCG parser are an order of magnitude faster
C04-1180 derivations produced by a wide-coverage CCG parser . Unlike the dependency structures
C04-1041 supertagging in a wide-coverage CCG parser which uses a log-linear model
C04-1041 result is an accurate wide-coverage CCG parser which is an order of magnitude
D09-1126 used to train fast and accurate CCG parsers ( Clark and Curran , 2007 ) .
D10-1072 model with a state-of-the-art CCG parser , potentially freeing the ranker
C04-1180 Semantic Representations from a CCG Parser </title> Johan Bos Stephen Clark
C04-1180 representations using a wide-coverage CCG parser , with a coverage of over 97
C04-1041 integrating a supertagger with a CCG parser , very fast parse times can be
D08-1050 and question GR resources . The CCG parser is particularly well suited to
D08-1050 parser . 2 The CCG Parser The CCG parser is described in detail in Clark
C04-1041 constraints for a wide-coverage CCG parser . 4.2 Results ( Space Requirements
D08-1050 for the newspaper version of the CCG parser are obtained from CCGbank ( Hocken
C04-1180 Hockenmaier , 2003 ) . The existing CCG parsers deliver predicate argument structures
D10-1068 train a model for the C&amp;C CCG parser . In that case , however , the
C04-1180 accurate , efficient and robust CCG parsers which can be used directly for
D08-1050 upper bound when evaluating a CCG parser on GRs , since some loss is inherent
hide detail