Paper: Chart Pruning for Fast Lexicalised-Grammar Parsing

ACL ID C10-2168
Title Chart Pruning for Fast Lexicalised-Grammar Parsing
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010

Given the increasing need to process mas- sive amounts of textual data, efficiency of NLP tools is becoming a pressing concern. Parsers based on lexicalised grammar for- malisms, such as TAG and CCG, can be made more efficient using supertagging, which for CCG is so effective that every derivation consistent with the supertagger output can be stored in a packed chart. However, wide-coverage CCG parsers still produce a very large number of deriva- tions for typical newspaper or Wikipedia sentences. In this paper we investigate two forms of chart pruning, and develop a novel method for pruning complete cells in a parse chart. The result is a wide- coverage CCG parser that can process al- most 100 sentences per second, with lit- tle or no loss in accuracy over the baseline with no pruning.