Non-Deterministic Oracles for Unrestricted Non-Projective Transition-Based Dependency Parsing

We study non-deterministic oracles for training non-projective beam search parsers with swap transitions. We map out the spurious ambiguities of the transition system and present two non-deterministic oracles as well as a static oracle that minimizes the number of swaps. An evaluation on 10 treebanks reveals that the difference between static and non-deterministic oracles is generally insignificant for beam search parsers but that non-deterministic oracles can improve the accuracy of greedy parsers that use swap transitions.

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

[2]  Yang Guo,et al.  Structured Perceptron with Inexact Search , 2012, NAACL.

[3]  Giorgio Satta,et al.  A Tabular Method for Dynamic Oracles in Transition-Based Parsing , 2014, TACL.

[4]  Giorgio Satta,et al.  A Polynomial-Time Dynamic Oracle for Non-Projective Dependency Parsing , 2014, EMNLP.

[5]  Giorgio Satta,et al.  A Transition-Based Dependency Parser Using a Dynamic Parsing Strategy , 2013, ACL.

[6]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[7]  Joakim Nivre,et al.  Non-Projective Dependency Parsing in Expected Linear Time , 2009, ACL.

[8]  Hinrich Schütze,et al.  Efficient Higher-Order CRFs for Morphological Tagging , 2013, EMNLP.

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

[10]  Joakim Nivre,et al.  Training Deterministic Parsers with Non-Deterministic Oracles , 2013, TACL.

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

[12]  Joakim Nivre,et al.  An Improved Oracle for Dependency Parsing with Online Reordering , 2009, IWPT.

[13]  Reut Tsarfaty,et al.  Introducing the SPMRL 2014 Shared Task on Parsing Morphologically-rich Languages , 2014 .

[14]  Weiguang Qu,et al.  Efficient Latent Structural Perceptron with Hybrid Trees for Semantic Parsing , 2013, IJCAI.

[15]  Eraldo Rezende Fernandes,et al.  Latent Structure Perceptron with Feature Induction for Unrestricted Coreference Resolution , 2012, EMNLP-CoNLL Shared Task.

[16]  Christopher D. Manning,et al.  Generating Typed Dependency Parses from Phrase Structure Parses , 2006, LREC.

[17]  Joakim Nivre,et al.  Transition-based Dependency Parsing with Rich Non-local Features , 2011, ACL.

[18]  Haitao Mi,et al.  Max-Violation Perceptron and Forced Decoding for Scalable MT Training , 2013, EMNLP.

[19]  Joakim Nivre,et al.  Feature Description for the Transition-Based Parser for Joint Part-of-Speech Tagging and Labeled Non-Projective Dependency Parsing , 2012 .

[20]  Joakim Nivre,et al.  An Efficient Algorithm for Projective Dependency Parsing , 2003, IWPT.

[21]  Brian Roark,et al.  Incremental Parsing with the Perceptron Algorithm , 2004, ACL.

[22]  Joakim Nivre,et al.  Joint Morphological and Syntactic Analysis for Richly Inflected Languages , 2013, TACL.

[23]  Giuseppe Attardi,et al.  Experiments with a Multilanguage Non-Projective Dependency Parser , 2006, CoNLL.

[24]  Joakim Nivre,et al.  A Transition-Based Parser for 2-Planar Dependency Structures , 2010, ACL.

[25]  Koby Crammer,et al.  Online Passive-Aggressive Algorithms , 2003, J. Mach. Learn. Res..

[26]  Bernd Bohnet,et al.  Top Accuracy and Fast Dependency Parsing is not a Contradiction , 2010, COLING.

[27]  Joakim Nivre,et al.  A Dynamic Oracle for Arc-Eager Dependency Parsing , 2012, COLING.