Beam-Width Prediction for Efficient Context-Free Parsing

Efficient decoding for syntactic parsing has become a necessary research area as statistical grammars grow in accuracy and size and as more NLP applications leverage syntactic analyses. We review prior methods for pruning and then present a new framework that unifies their strengths into a single approach. 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, exemplified 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.

[1]  Michael Collins,et al.  Three Generative, Lexicalised Models for Statistical Parsing , 1997, ACL.

[2]  Daniel Marcu,et al.  Learning as search optimization: approximate large margin methods for structured prediction , 2005, ICML.

[3]  Dan Klein,et al.  Learning Accurate, Compact, and Interpretable Tree Annotation , 2006, ACL.

[4]  James R. Curran,et al.  Chart Pruning for Fast Lexicalised-Grammar Parsing , 2010, COLING.

[5]  Wen-Lian Hsu,et al.  Exploiting Full Parsing Information to Label Semantic Roles Using an Ensemble of ME and SVM via Integer Linear Programming , 2005, CoNLL.

[6]  Brian Roark,et al.  Unary Constraints for Efficient Context-Free Parsing , 2011, ACL.

[7]  Jun'ichi Tsujii,et al.  Probabilistic CFG with Latent Annotations , 2005, ACL.

[8]  Dan Klein,et al.  Accurate Unlexicalized Parsing , 2003, ACL.

[9]  Joakim Nivre,et al.  Algorithms for Deterministic Incremental Dependency Parsing , 2008, CL.

[10]  Eugene Charniak,et al.  Figures of Merit for Best-First Probabilistic Chart Parsing , 1998, Comput. Linguistics.

[11]  David Chiang,et al.  Learning to Translate with Source and Target Syntax , 2010, ACL.

[12]  Robert J. Bobrow.  Statistical Agenda Parsing , 1991, HLT.

[13]  Michael Collins,et al.  Head-Driven Statistical Models for Natural Language Parsing , 2003, CL.

[14]  Slav Petrov,et al.  Uptraining for Accurate Deterministic Question Parsing , 2010, EMNLP.

[15]  Brian Roark,et al.  Classifying Chart Cells for Quadratic Complexity Context-Free Inference , 2008, COLING.

[16]  Dan Klein,et al.  Improved Inference for Unlexicalized Parsing , 2007, NAACL.

[17]  Eugene Charniak,et al.  A Maximum-Entropy-Inspired Parser , 2000, ANLP.

[18]  Brian Roark,et al.  Exponential Decay Pruning for Bottom-Up Beam-Search Parsing , 2010 .

[19]  Brian Roark,et al.  Linear Complexity Context-Free Parsing Pipelines via Chart Constraints , 2009, NAACL.

[20]  Michael Collins,et al.  Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms , 2002, EMNLP.

[21]  Marti A. Hearst,et al.  HLT-NAACL 2003 : Human Language Technology conference of the North American Chapter of the Association for Computational Linguistics : proceedings of the main conference : May 27 to June 1, 2003, Edmonton, Alberta, Canada , 2003 .

[22]  Dan Klein,et al.  Top-Down K-Best A* Parsing , 2010, ACL.

[23]  Dan Klein,et al.  Learning and Inference for Hierarchically Split PCFGs , 2007, AAAI.

[24]  Mark Johnson,et al.  PCFG Models of Linguistic Tree Representations , 1998, CL.

[25]  Joshua Goodman,et al.  Global Thresholding and Multiple-Pass Parsing , 1997, EMNLP.

[26]  Eugene Charniak,et al.  Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking , 2005, ACL.

[27]  Dan Roth,et al.  The Importance of Syntactic Parsing and Inference in Semantic Role Labeling , 2008, CL.

[28]  Dan Klein,et al.  A* Parsing: Fast Exact Viterbi Parse Selection , 2003, NAACL.