Object-Extraction and Question-Parsing using CCG.
Stephen Clark, Mark J. Steedman, James Curran · Edinburgh Research Explorer (University of Edinburgh) · 2004
Accurate dependency recovery has recently been reported for a number of wide-coverage statistical parsers using CombinatoryCategorialGrammar (CCG). However, overall figures give no indication of a parser’s performance on specific constructions, nor how suitable a parser is for specific applications. In this paper we givea detailed evaluation of a CCG parser on object extraction dependencies found in WSJ text.We also show how the parser can be used to parse questions for Question Answering. Theaccuracy of the original parser on questions is very poor, and we propose a novel technique forporting the parser to a new domain, by creatingn ew labelled data at the lexical category levelonly. Using a super tagger to assign categoriesto words, trained on the new data, leads to a dramatic increase in question parsing accuracy