Extraction of Syntactic Structures Based on the Czech Parser Synt

In this paper we describe the usage of the syntactic parser synt (developed in the NLP Centre at Masaryk University) to gain information about syntactic structures (such as noun or verb phrases) of common sentences in Czech. These structures are from the analysis point of view usually identical to nonterminals in the grammar used by the parser to find possible valid derivations of the given sentence. The parser has been extended in such a way that enables its highly ambiguous output to be used for extracting those syntactic structures unambiguously and gives several ways how to identify them. To achieve this, some previously unused results of syntactic analysis have been evolved leading to more precise morphological analysis and hence also deeper distinction among various syntactic (sub)structures. Finally, we present an application for shallow valency extraction.