Model of a Parser for Croatian Language

Statistics

Downloads

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].

Preview

PDF (Croatian)
Download (4MB) | Preview

Abstract

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:

URL	URL Type
https://bib.irb.hr/prikazi-rad?&rad=388476	UNSPECIFIED

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

URI:

http://darhiv.ffzg.unizg.hr/id/eprint/2343

Actions (login required)

View Item

Faculty of Humanities and Social Sciences Institutional Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.