Jointly or Separately: Which is Better for Parsing Heterogeneous Dependencies?

For languages such as English, several constituent-to-dependency conversion schemes are proposed to construct corpora for dependency parsing. It is hard to determine which scheme is better because they reflect different views of dependency analysis. We usually obtain dependency parsers of different schemes by training with the specific corpus separately. It neglects the correlations between these schemes, which can potentially benefit the parsers. In this paper, we study how these correlations influence final dependency parsing performances, by proposing a joint model which can make full use of the correlations between heterogeneous dependencies, and finally we can answer the following question: parsing heterogeneous dependencies jointly or separately, which is better? We conduct experiments with two different schemes on the Penn Treebank and the Chinese Penn Treebank respectively, arriving at the same conclusion that jointly parsing heterogeneous dependencies can give improved performances for both schemes over the individual models.

[1]  Hitoshi Isahara,et al.  An Error-Driven Word-Character Hybrid Model for Joint Chinese Word Segmentation and POS Tagging , 2009, ACL/IJCNLP.

[2]  Hao Zhang,et al.  Generalized Higher-Order Dependency Parsing with Cube Pruning , 2012, EMNLP.

[3]  Yue Zhang,et al.  Chinese Parsing Exploiting Characters , 2013, ACL.

[4]  Christopher D. Manning,et al.  The Stanford Typed Dependencies Representation , 2008, CF+CDPE@COLING.

[5]  Yue Zhang,et al.  Character-Level Chinese Dependency Parsing , 2014, ACL.

[6]  Michael Collins,et al.  Efficient Third-Order Dependency Parsers , 2010, ACL.

[7]  Hao Zhang,et al.  Online Learning for Inexact Hypergraph Search , 2013, EMNLP.

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

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

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

[11]  Stephen Clark,et al.  A Fast Decoder for Joint Word Segmentation and POS-Tagging Using a Single Discriminative Model , 2010, EMNLP.

[12]  Andrew McCallum,et al.  Transition-based Dependency Parsing with Selectional Branching , 2013, ACL.

[13]  Hao Zhang,et al.  Enforcing Structural Diversity in Cube-pruned Dependency Parsing , 2014, ACL.

[14]  Sigrid Klerke,et al.  Down-stream effects of tree-to-dependency conversions , 2013, HLT-NAACL.

[15]  Qun Liu,et al.  Automatic Adaptation of Annotation Standards: Chinese Word Segmentation and POS Tagging - A Case Study , 2009, ACL/IJCNLP.

[16]  Jun'ichi Tsujii,et al.  Incremental Joint POS Tagging and Dependency Parsing in Chinese , 2011, IJCNLP.

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

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

[19]  Alexander M. Rush,et al.  Vine Pruning for Efficient Multi-Pass Dependency Parsing , 2012, NAACL.

[20]  Noah A. Smith,et al.  An Empirical Comparison of Parsing Methods for Stanford Dependencies , 2014, ArXiv.

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

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

[23]  Stephen Clark,et al.  Syntactic Processing Using the Generalized Perceptron and Beam Search , 2011, CL.

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

[25]  Noah A. Smith,et al.  Turning on the Turbo: Fast Third-Order Non-Projective Turbo Parsers , 2013, ACL.

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

[27]  Weiwei Sun,et al.  Reducing Approximation and Estimation Errors for Chinese Lexical Processing with Heterogeneous Annotations , 2012, ACL.

[28]  Qun Liu,et al.  A Cascaded Linear Model for Joint Chinese Word Segmentation and Part-of-Speech Tagging , 2008, ACL.

[29]  Wanxiang Che,et al.  Exploiting Multiple Treebanks for Parsing with Quasi-synchronous Grammars , 2012, ACL.

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

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

[32]  Joakim Nivre,et al.  A Transition-Based System for Joint Part-of-Speech Tagging and Labeled Non-Projective Dependency Parsing , 2012, EMNLP.

[33]  Jun Zhao,et al.  Joint Inference for Heterogeneous Dependency Parsing , 2013, ACL.

[34]  Haizhou Li,et al.  Joint Models for Chinese POS Tagging and Dependency Parsing , 2011, EMNLP.

[35]  Jun'ichi Tsujii,et al.  Incremental Joint Approach to Word Segmentation, POS Tagging, and Dependency Parsing in Chinese , 2012, ACL.