An Efficient Algorithm for Easy-First Non-Directional Dependency Parsing

We present a novel deterministic dependency parsing algorithm that attempts to create the easiest arcs in the dependency structure first in a non-directional manner. Traditional deterministic parsing algorithms are based on a shift-reduce framework: they traverse the sentence from left-to-right and, at each step, perform one of a possible set of actions, until a complete tree is built. A drawback of this approach is that it is extremely local: while decisions can be based on complex structures on the left, they can look only at a few words to the right. In contrast, our algorithm builds a dependency tree by iteratively selecting the best pair of neighbours to connect at each parsing step. This allows incorporation of features from already built structures both to the left and to the right of the attachment point. The parser learns both the attachment preferences and the order in which they should be performed. The result is a deterministic, best-first, O(nlogn) parser, which is significantly more accurate than best-first transition based parsers, and nears the performance of globally optimized parsing models.

[1]  Alon Lavie,et al.  A Best-First Probabilistic Shift-Reduce Parser , 2006, ACL.

[2]  Sebastian Riedel,et al.  Incremental Integer Linear Programming for Non-projective Dependency Parsing , 2006, EMNLP.

[3]  Sabine Buchholz,et al.  CoNLL-X Shared Task on Multilingual Dependency Parsing , 2006, CoNLL.

[4]  Joakim Nivre,et al.  MaltParser: A Data-Driven Parser-Generator for Dependency Parsing , 2006, LREC.

[5]  Noah A. Smith,et al.  Parsing with Soft and Hard Constraints on Dependency Length , 2005, IWPT.

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

[7]  Aravind K. Joshi,et al.  LTAG Dependency Parsing with Bidirectional Incremental Construction , 2008, EMNLP.

[8]  Giorgio Satta,et al.  Guided Learning for Bidirectional Sequence Classification , 2007, ACL.

[9]  Ivan Titov,et al.  Fast and Robust Multilingual Dependency Parsing with a Generative Latent Variable Model , 2007, EMNLP.

[10]  Noah A. Smith,et al.  Parsing with Soft and Hard Constraints on Dependency Length , 2005 .

[11]  Tetsuji Nakagawa,et al.  Multilingual Dependency Parsing Using Global Features , 2007, EMNLP.

[12]  Joakim Nivre,et al.  Characterizing the Errors of Data-Driven Dependency Parsing Models , 2007, EMNLP.

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

[14]  Qun Liu,et al.  Bilingually-Constrained (Monolingual) Shift-Reduce Parsing , 2009, EMNLP.

[15]  Sebastian Riedel,et al.  The CoNLL 2007 Shared Task on Dependency Parsing , 2007, EMNLP.

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

[17]  Joakim Nivre,et al.  Integrating Graph-Based and Transition-Based Dependency Parsers , 2008, ACL.

[18]  Stephen Clark,et al.  A Tale of Two Parsers: Investigating and Combining Graph-based and Transition-based Dependency Parsing , 2008, EMNLP.

[19]  Joakim Nivre,et al.  Incrementality in Deterministic Dependency Parsing , 2004 .

[20]  Fernando Pereira,et al.  Online Learning of Approximate Dependency Parsing Algorithms , 2006, EACL.

[21]  Federico Sangati,et al.  An English dependency treebank à la Tesnière , 2009 .

[22]  Alon Lavie,et al.  Parser Combination by Reparsing , 2006, NAACL.

[23]  Xavier Carreras,et al.  Experiments with a Higher-Order Projective Dependency Parser , 2007, EMNLP.

[24]  Noah A. Smith,et al.  Vine Parsing and Minimum Risk Reranking for Speed and Precision , 2006, CoNLL.

[25]  Richard Johansson,et al.  Extended Constituent-to-Dependency Conversion for English , 2007, NODALIDA.