论文信息 - Adaptation of Czech Parsers for Slovak

Adaptation of Czech Parsers for Slovak

Abstract. In this paper we present an adaptation of two Czech syntactic analyzers Synt and SET for Slovak language. We describe the transformation of Slovak morphological tagset used by the Slovak development corpora skTenTen and r-mak-3.0 to its Czech equivalent expected by the parsers and modifications of both parsers that have been performed partially in the lexical analysis and mainly in the formal grammars used in both systems. Finally we provide an evaluation of parsing results on two datasets – a phrasal and dependency treebank of Slovak.

Vojtech Kovár | Milos Jakubícek | Marek Medved | Václav Nemcík

[1] Vojtech Kovár,et al. Czech Morphological Tagset Revisited , 2011, RASLAN.

[2] Ales Horák,et al. Mining Phrases from Syntactic Analysis , 2009, TSD.

[3] Geoffrey Sampson,et al. A test of the leaf-ancestor metric for parse accuracy , 2003, Natural Language Engineering.

[4] Jozef Juhár,et al. Extracting Sentence Elements for the Natural Language Understanding Based on Slovak National Corpus , 2010, COST 2102 Conference.

[5] Pavel Smerk. Fast Morphological Analysis of Czech , 2009, RASLAN.

[6] Ales Horák,et al. Syntactic Analysis Using Finite Patterns: A New Parsing System for Czech , 2009, LTC.

[7] Vasek Nemcík,et al. Extracting Phrases from PDT 2.0 , 2011, RASLAN.

[8] Mária Bieliková,et al. Realization of Syntactic Parser for Inflectional Language Using XML and Regular Expressions , 2000, TSD.