Constraints on Non-Projective Dependency Parsing

We investigate a series of graph-theoretic constraints on non-projective dependency parsing and their effect on expressivity, i.e. whether they allow naturally occurring syntactic constructions to be adequately represented, and efficiency, i.e. whether they reduce the search space for the parser. In particular, we define a new measure for the degree of non-projectivity in an acyclic dependency graph obeying the single-head constraint. The constraints are evaluated experimentally using data from the Prague Dependency Treebank and the Danish Dependency Treebank. The results indicate that, whereas complete linguistic coverage in principle requires unrestricted non-projective dependency graphs, limiting the degree of non-projectivity to at most 2 can reduce average running time from quadratic to linear, while excluding less than 0.5% of the dependency graphs found in the two treebanks. This is a substantial improvement over the commonly used projective approximation (degree 0), which excludes 15–25% of the graphs.

[1]  Amit Dubey,et al.  Deep Syntactic Processing by Combining Shallow Methods , 2003, ACL.

[2]  Roger Levy,et al.  Deep Dependencies from Context-Free Statistical Parsers: Correcting the Surface Dependency Approximation , 2004, ACL.

[3]  M. Trautner,et al.  The Danish Dependency Treebank and the DTAG Treebank Tool , 2003 .

[4]  Joakim Nivre,et al.  Memory-Based Dependency Parsing , 2004, CoNLL.

[5]  Koby Crammer,et al.  Online Large-Margin Training of Dependency Parsers , 2005, ACL.

[6]  Haim Gaifman,et al.  Dependency Systems and Phrase-Structure Systems , 1965, Inf. Control..

[7]  李幼升,et al.  Ph , 1989 .

[8]  Andy Way,et al.  Long-Distance Dependency Resolution in Automatically Acquired Wide-Coverage PCFG-Based LFG Approximations , 2004, ACL.

[9]  Richard Hudson,et al.  English word grammar , 1995 .

[10]  Mark Johnson,et al.  A Simple Pattern-matching Algorithm for Recovering Empty Nodes and their Antecedents , 2002, ACL.

[11]  Oliver Plaehn,et al.  Computing the Most Probable Parse for a Discontinuous Phrase Structure Grammar , 2000, IWPT.

[12]  Jason Eisner,et al.  Bilexical Grammars and their Cubic-Time Parsing Algorithms , 2000 .

[13]  Fernando Pereira,et al.  Non-Projective Dependency Parsing using Spanning Tree Algorithms , 2005, HLT.

[14]  Jan Hajic,et al.  The Prague Dependency Treebank , 2003 .

[15]  Richard Campbell,et al.  Using Linguistic Principles to Recover Empty Categories , 2004, ACL.

[16]  Igor Mel’čuk,et al.  Dependency Syntax: Theory and Practice , 1987 .

[17]  Michael Collins,et al.  A Statistical Parser for Czech , 1999, ACL.

[18]  Yuji Matsumoto,et al.  Statistical Dependency Analysis with Support Vector Machines , 2003, IWPT.

[19]  Michael A. Covington,et al.  A Fundamental Algorithm for Dependency Parsing , 2004 .

[20]  Peter Neuhaus,et al.  The Complexity of Recognition of Linguistically Adequate Dependency Grammars , 1997, ACL.

[21]  Hiroshi Maruyama,et al.  Structural Disambiguation With Constraint Propagation , 1990, ACL.

[22]  Joakim Nivre,et al.  Pseudo-Projective Dependency Parsing , 2005, ACL.

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

[24]  Alexis Nasr,et al.  Pseudo-Projectivity, A Polynomially Parsable Non-Projective Dependency Grammar , 1998, ACL.

[25]  Valentin Jijkoun,et al.  Enriching the Output of a Parser Using Memory-based Learning , 2004, ACL.

[26]  Petr Sgall,et al.  The Meaning Of The Sentence In Its Semantic And Pragmatic Aspects , 1986 .