Speed and accuracy in shallow and deep stochastic parsing
This paper reports some initial experiments that compare the accuracy and performance of two stochastic parsing systems. The currently popular Collins parser is a shallow parser whose output contains more detailed semantically-relevant information than other such parsers. The XLE parser is a deep-parsing system that couples a Lexical Functional Grammar to a log-linear disambiguation component and provides the much richer representations of LFG theory. We measured the accuracy of both systems against a gold standard of the PARC 700 dependency bank, and also measured their processing times. We found that the deep-parsing system to be significantly more accurate than the Collins parser with only a slight reduction in parsing speed.
Kaplan, R. M. ; Riezler, S ; King, T. H. ; Maxwell, J. T. ; Vasserman, A. Speed and accuracy in shallow and deep stochastic parsing. Human Language Technology Conference/North American Chapter of the Association for Computational Linguistics Meeting; 2004 May 2-7; Boston; MA.