Seminar — Stephen Clark

In this talk I will describe the C&C parser, a a state-of-the-art, linguistically motivated statistical parser based on Combinatory Categorial Grammar, and describe some experiments on adapting the parser to the biomedical domain. The parser was originally developed using the Penn Treebank and is therefore tuned to newspaper text. The proposed porting approach takes advantage of the lexicalized nature of CCG to train the parser at a lower level of representation than full syntactic derivations. The CCG parser uses three levels of representation: a first level consisting of part-of-speech tags; a second level consisting of more fine-grained CCG lexical categories; and a third, hierarchical level consisting of CCG derivations. We find that simply retraining the POS tagger on biomedical data leads to a large improvement in performance, and that using annotated data at the intermediate lexical category level of representation improves parsing accuracy further. The parsing accuracies obtained for biomedical data are in the same range as those reported for newspaper text, and higher than those previously reported for the biomedical resource on which the parser is evaluated. The conclusion is that porting newspaper parsers to the biomedical domain, at least for parsers which use lexicalized grammars, may not be as difficult as first thought.