1. UKM Learning and Research Repository
2. Master Thesis / Tesis Master
3. Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat

Title:	Arabic Malay machine translation for a dialogue system
Authors:	Almeshrky Hamida Ali. (P50169)
Supervisor:	Mohd. Juzaiddin Ab Aziz, Dr.
Keywords:	Natural language processing (Computer science). Machine translation
Issue Date:	7-Apr-2011
Description:	Machine translation (MT) has been defined as the process that utilizes computer software to translate text from one natural language to another. This research will work on Arabic to Malay language for a dialogue system. The challenge in this research is that Arabic and Malay language are constructed in different structures such as free-word-order, pro–drop subject when it is attached as pronouns in word. To address such the challenges in the system, the main goal of this research is to translate Arabic-Malay language dialogue system based on the transfer approach. This approach is considered as one of the categories rule based approaches and it is one of the most widely used methods of machine translation. The idea behind transfer approach is to translate the language based on linguistic knowledge of both the source and target language. It is not translates at the lexical level only, but it can translate between different structures syntactically and sometimes semantically. The MT system consists of three main components: analysis, transfer, and generation component. The first analysis stage is analyzed the source language into target language where the dependent representation with a set of features such as part of speech (POS) will be used. The second transfer stage involves applied a set of transfer rules, to transform underlying representation of the source sentence into representation which contains features of the target language. Eventually, the generation module takes the representation from previous stage as input and produces the target language output. Considering the system evaluations tested on set of dialogues that includes the general university campus dialogue from variety teaching of Arabic language dialogue books. The accuracy is 89.4% as result of comparing between human translation and the system. The accuracy shows that the transfer base approach is viable to translate a dialogue between Arabic and Malay languages.,Master
Pages:	80
Call Number:	QA76.9.N38 A57 2011
Publisher:	UKM, Bangi
Appears in Collections:	Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.