A Unified Morpho-Syntactic Scheme of Stanford Dependencies

Stanford Dependencies (SD) provide a functional characterization of the grammatical relations in syntactic parse-trees. The SD representation is useful for parser evaluation, for downstream applications, and, ultimately, for natural language understanding, however, the design of SD focuses on structurally-marked relations and under-represents morphosyntactic realization patterns observed in Morphologically Rich Languages (MRLs). We present a novel extension of SD, called Unified-SD (U-SD), which unifies the annotation of structurallyand morphologically-marked relations via an inheritance hierarchy. We create a new resource composed of U-SDannotated constituency and dependency treebanks for the MRL Modern Hebrew, and present two systems that can automatically predict U-SD annotations, for gold segmented input as well as raw texts, with high baseline accuracy.

[1]  Paul M. Postal,et al.  Toward a Universal Characterization of Passivization , 1977 .

[2]  Yoav Goldberg,et al.  Easy-First Dependency Parsing of Modern Hebrew , 2010, SPMRL@NAACL-HLT.

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

[4]  L. Glinert.  The Grammar of Modern Hebrew , 1989 .

[5]  Mary Dalrymple,et al.  The PARC 700 Dependency Bank , 2003, LINC@EACL.

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

[7]  Joakim Nivre,et al.  Universal Dependency Annotation for Multilingual Parsing , 2013, ACL.

[8]  Yoav Goldberg,et al.  Joint Hebrew Segmentation and Parsing using a PCFGLA Lattice Parser , 2011, ACL.

[9]  N. Ohashi,et al.  Agreement , 2002 .

[10]  Yuji Matsumoto.  MaltParser: A language-independent system for data-driven dependency parsing , 2005 .

[11]  Daniel Jurafsky,et al.  Parsing to Stanford Dependencies: Trade-offs between Speed and Accuracy , 2010, LREC.

[12]  Ido Dagan,et al.  The Third PASCAL Recognizing Textual Entailment Challenge , 2007, ACL-PASCAL@ACL.

[13]  Yannick Versley,et al.  Statistical Parsing of Morphologically Rich Languages (SPMRL) What, How and Whither , 2010, SPMRL@NAACL-HLT.

[14]  Owen Rambow.  The Simple Truth about Dependency and Phrase Structure Representations: An Opinion Piece , 2010, HLT-NAACL.

[15]  Evelina Andersson,et al.  Cross-Framework Evaluation for Statistical Parsing , 2012, EACL.

[16]  Valentin I. Spitkovsky,et al.  A Comparison of Chinese Parsers for Stanford Dependencies , 2012, ACL.

[17]  Ralf Zimmer,et al.  RelEx - Relation extraction using dependency parse trees , 2007, Bioinform..

[18]  Michael Elhadad,et al.  An Unsupervised Morpheme-Based HMM for Hebrew Morphological Disambiguation , 2006, ACL.

[19]  Khalil Sima'an,et al.  Building a tree-bank of modern hebrew text , 2001 .

[20]  Joakim Nivre,et al.  Evaluation of Dependency Parsers on Unbounded Dependencies , 2010, COLING.

[21]  Stephen R. Anderson,et al.  A-Morphous morphology , 1992 .

[22]  Khalil Sima'an,et al.  Relational-Realizational Parsing , 2008, COLING.

[23]  Dan Klein,et al.  Learning Accurate, Compact, and Interpretable Tree Annotation , 2006, ACL.

[24]  J. Bresnan.  Lexical-Functional Syntax , 2000 .

[25]  Sabine Brants,et al.  The TIGER Treebank , 2001 .

[26]  Tapio Salakoski,et al.  A Dependency-based Analysis of Treebank Annotation Errors , 2011, DepLing.