Multi-Tagging for Lexicalized-Grammar Parsing

With performance above 97% accuracy for newspaper text, part of speech (POS) tagging might be considered a solved problem. Previous studies have shown that allowing the parser to resolve POS tag ambiguity does not improve performance. However, for grammar formalisms which use more fine-grained grammatical categories, for example TAG and CCG, tagging accuracy is much lower. In fact, for these formalisms, premature ambiguity resolution makes parsing infeasible.We describe a multi-tagging approach which maintains a suitable level of lexical category ambiguity for accurate and efficient CCG parsing. We extend this multi-tagging approach to the POS level to overcome errors introduced by automatically assigned POS tags. Although POS tagging accuracy seems high, maintaining some POS tag ambiguity in the language processing pipeline results in more accurate CCG supertagging.

[1]  Ted Briscoe,et al.  Robust Accurate Statistical Annotation of General Text , 2002, LREC.

[2]  Stanley F. Chen,et al.  A Gaussian Prior for Smoothing Maximum Entropy Models , 1999 .

[3]  Hinrich Schütze,et al.  Book Reviews: Foundations of Statistical Natural Language Processing , 1999, CL.

[4]  James R. Curran,et al.  Parsing the WSJ Using CCG and Log-Linear Models , 2004, ACL.

[5]  Rob Malouf,et al.  A Comparison of Algorithms for Maximum Entropy Parameter Estimation , 2002, CoNLL.

[6]  James R. Curran,et al.  Tagging Unknown Words with Raw Text Features , 2005, ALTA.

[7]  Martin Kay,et al.  Syntactic Process , 1979, ACL.

[8]  John D. Lafferty,et al.  Inducing Features of Random Fields , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[10]  James R. Curran,et al.  Investigating GIS and Smoothing for Maximum Entropy Taggers , 2003, EACL.

[11]  Glenn Carroll,et al.  Taggers for Parsers , 1996, Artif. Intell..

[12]  Dan Roth,et al.  A Linear Programming Formulation for Global Inference in Natural Language Tasks , 2004, CoNLL.

[13]  Mark Steedman,et al.  Generative Models for Statistical Parsing with Combinatory Categorial Grammar , 2002, ACL.

[14]  van Gerardus Noord,et al.  Reinforcing Parser Preferences through Tagging , 2004 .

[15]  Bangalore Srinivas.  A lightweight dependency analyzer for partial parsing , 2000 .

[16]  Dan Klein,et al.  Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network , 2003, NAACL.

[17]  Rebecca Watson.  Part-of-speech tagging models for parsing , 2006 .

[18]  Gertjan van Noord,et al.  Reinforcing parser preferences through tagging : Évolutions en analyse syntaxique , 2003 .

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

[20]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[21]  Julia Hockenmaier,et al.  Data and models for statistical parsing with combinatory categorial grammar , 2003 .

[22]  Srinivas Bangalore,et al.  Supertagging: An Approach to Almost Parsing , 1999, CL.

[23]  Christopher D. Manning,et al.  Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger , 2000, EMNLP.

[24]  James R. Curran,et al.  The Importance of Supertagging for Wide-Coverage CCG Parsing , 2004, COLING.