Paper: Beam-Width Prediction for Efficient Context-Free Parsing

ACL ID P11-1045
Title Beam-Width Prediction for Efficient Context-Free Parsing
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011

Efficient decoding for syntactic parsing has become a necessary research area as statisti- cal grammars grow in accuracy and size and as more NLP applications leverage syntac- tic analyses. We review prior methods for pruning and then present a new framework that unifies their strengths into a single ap- proach. Using a log linear model, we learn the optimal beam-search pruning parameters for each CYK chart cell, effectively predicting the most promising areas of the model space to explore. We demonstrate that our method is faster than coarse-to-fine pruning, exempli- fied in both the Charniak and Berkeley parsers, by empirically comparing our parser to the Berkeley parser using the same grammar and under identical operating conditions.