Please use this identifier to cite or link to this item: https://www.um.edu.mt/library/oar/handle/123456789/95503
Title: Extending the GF framework towards coverage of the maltese language
Authors: Zammit, Angelo (2012)
Keywords: Computational linguistics
Natural language processing (Computer science)
Maltese language
Parsing (Computer grammar)
Issue Date: 2012
Citation: Zammit, A. (2012). Extending the GF framework towards coverage of the maltese language (Bachelor's dissertation).
Abstract: The aim of this work is to develop language resources for Maltese suitable for incorporation into an eventual Machine Translation. The Grammatical Framework (Ranta, 2004) was identified as an increasingly well-recognised programming environment suitable for the creation of domain-specific natural language applications including high quality, accurate translations. Although the Grammatical Framework has resource grammars for over 20 languages, support for Maltese was is still highly fragmentary. Work on the lexical and morphological aspects of Maltese within this framework had previously been carried out however this only enabled translation at word level. This project was focused on extending the existing Maltese resource grammar in order to support translation at phrase and sentence level within this framework. In this regard, particular emphasis was given to the syntactic aspects of the Maltese language in addition to the implementation of missing morphological rules. Evaluation of the resulting work concludes that although the extended Maltese resource grammar is sufficient to translate a number of simple sentences correctly, further work is required to improve the coverage and correctness of the resource grammar created during this project.
Description: B.Sc. IT (Hons)(Melit.)
URI: https://www.um.edu.mt/library/oar/handle/123456789/95503
Appears in Collections:Dissertations - FacICT - 2012
Dissertations - FacICTCS - 2010-2015

Files in This Item:
File Description SizeFormat 
BSC(HONS)ICT_Zammit, Angelo_2012.pdf
  Restricted Access
3.87 MBAdobe PDFView/Open Request a copy


Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.