Improving the efficiency of a wide-coverage CCG parser

Abstract

The C&C CCG parser is a highly efficient linguistically motivated parser. The efficiency is achieved using a tightly-integrated supertagger, which assigns CCG lexical categories to words in a sentence. The integration allows the parser to request more categories if it cannot find a spanning analysis. We present several enhancements to the CKY chart parsing algorithm used by the parser. The first proposal is chart repair, which allows the chart to be efficiently updated by adding lexical categories individually, and we evaluate several strategies for adding these categories. The second proposal is to add constraints to the chart which require certain spans to be constituents. Finally, we propose partial beam search to further reduce the search space. Overall, the parsing speed is improved by over 35% with negligible loss of accuracy or coverage.