On the Importance of Ezafe Construction in Persian Parsing

Ezafe construction is an idiosyncratic phenomenon in the Persian language. It is a good indicator for phrase boundaries and dependency relations but mostly does not appear in the text. In this paper, we show that adding information about Ezafe construction can give 4.6% relative improvement in dependency parsing and 9% relative improvement in shallow parsing. For evaluation purposes, Ezafe tags are manually annotated in the Persian dependency treebank. Furthermore, to be able to conduct experiments on shallow parsing, we develop a dependency to shallow phrase structure convertor based on the Persian dependencies.

[1]  Michael A. Covington.  Parsing Discontinuous constituents in Dependency Grammar , 1990, CL.

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

[3]  Heshaam Faili,et al.  A Probabilistic Approach to Persian Ezafe Recognition , 2014, EACL.

[4]  Jonas Kuhn,et al.  Morphological and Syntactic Case in Statistical Dependency Parsing , 2013, Computational Linguistics.

[5]  P. Samvelian,et al.  When Morphology Does Better than Syntax When Morphology Does Better than Syntax: the Ezafe Construction in Persian , 2022 .

[6]  Khaled Shaalan.  Nizar Y. Habash, Introduction to Arabic natural language processing (Synthesis lectures on human language technologies) , 2011, Machine Translation.

[7]  Mojgan Seraji,et al.  Dependency Parsers for Persian , 2012, ALR@COLING.

[8]  Mehrnoush Shamsfard,et al.  A Hybrid Algorithm for Recognizing the Position of Ezafe Constructions in Persian Texts , 2014, Int. J. Interact. Multim. Artif. Intell..

[9]  Jila Ghomeshi,et al.  Non-Projecting Nouns and the Ezafe: Construction in Persian , 1997 .

[10]  Behrouz Minaei-Bidgoli,et al.  An Empirical Study on the Effect of Morphological and Lexical Features in Persian Dependency Parsing , 2013, SPMRL@EMNLP.

[11]  Nizar Habash,et al.  Introduction to Arabic Natural Language Processing , 2010, Introduction to Arabic Natural Language Processing.

[12]  Mahmood Bijankhan,et al.  Lessons from building a Persian written corpus: Peykare , 2011, Lang. Resour. Evaluation.

[13]  Joakim Nivre,et al.  MaltOptimizer: A System for MaltParser Optimization , 2012, LREC.

[14]  Mohammad Sadegh Rasooli,et al.  Development of a Persian Syntactic Dependency Treebank , 2013, NAACL 2013.

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

[16]  François Yvon,et al.  Practical Very Large Scale CRFs , 2010, ACL.

[17]  Masood Ghayoomi,et al.  Word Clustering for Persian Statistical Parsing , 2012, JapTAL.

[18]  Mehrnoush Shamsfard,et al.  Developing a persian chunker using a hybrid approach , 2009, 2009 International Multiconference on Computer Science and Information Technology.

[19]  Nizar Habash,et al.  Overview of the SPMRL 2013 Shared Task: A Cross-Framework Evaluation of Parsing Morphologically Rich Languages , 2013, SPMRL@EMNLP.

[20]  Mohammad Sadegh Rasooli,et al.  Yara Parser: A Fast and Accurate Dependency Parser , 2015, ArXiv.