Knjižnica Filozofskog fakulteta
Sveučilišta u Zagrebu
Faculty of Humanities and Social Sciences Institutional Repository

Model of a Parser for Croatian Language


Downloads per month over past year

Vučković, Kristina. (2009). Model of a Parser for Croatian Language. PhD Thesis. Filozofski fakultet u Zagrebu, Department of Information Science. [mentor Dovedan Han, Zdravko and Tadić, Marko].

PDF (Croatian)
Download (4MB) | Preview


The paper describes the model of a partial shallow data driven parser. The analysis data is presented in a linear fashion using XML notation. Also, the first chunker for Croatian language is presented. Both models use dependency grammar and cascaded local grammars that describe noun chunks, apposition chunks, attribute chunks, verb chunks and prepositional chunks. The main grammars for the recognition of chunks are further more enhanced with the description of verb valency frames that are described in the Croatian valency lexicon CROVALLEX. Large percentage of ambiguous noun chunks has been disambiguated in this way.

Item Type: PhD Thesis
Related URLs:
Uncontrolled Keywords: parsing, partial parser, natural language, chunker, grammar, local grammars
Subjects: Information sciences > Social-humanistic informatics
Departments: Department of Information Science
Supervisor: Dovedan Han, Zdravko and Tadić, Marko
Date Deposited: 04 Oct 2013 10:36
Last Modified: 07 Dec 2016 10:32

Actions (login required)

View Item View Item