VOL. 13, NO. 12, JUNE 2018 ISSN 1819-6608 ARPN Journal of Engineering and Applied Sciences ©2006-2018 Asian Research Publishing Network (ARPN). All rights reserved. www.arpnjournals.com 3961 EVALUATION OF MACHINE TRANSLATION SYSTEMS AND RELATED PROCEDURES Musatafa Abbas Abbood Albadr 1 , Sabrina Tiun 1 and Fahad Taha Al-Dhief 2 1 Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia 2 Faculty of Electrical Engineering, Department of Communication Engineering, Universiti Teknologi Malaysia, Bahru, Johor, Malaysia E-Mail: mustafa_abbas1988@yahoo.com ABSTRACT Currently, the high volume of international information exchange involves a wide range of localities. As each locality comes with its own distinctive dialect, the need for an effective means of language translation is becoming more and more apparent. Among the concerns of information professionals is the capacity of an interested party to access web information offered in an unfamiliar language. Classified under the wide field of artificial intelligence, machine translation (MT) is an approach related to natural language processing. The machine translation technique involves the use of software for the conversion of documents or verbalized information from one natural language into another. Of late, a substantial number of procedures have been proposed for the fashioning of an efficient MT system. While these procedures were observed to be capable in certain areas, they were found wanting in others. The objectives of this endeavour are to (a) conduct a thorough investigation on machine translation and track its progress over recent decades, (b) examine the currently available machine translation procedures and systems and (c) offer an assessment on machine translation systems. Keywords: machine translation, rule based machine translation, corpus based machine translation, hybrid machine translation. 1. INTRODUCTION Natural language processing (NLP), which is an area of computer science and linguistics, focuses on the aspect of interaction between computers and human (natural) languages [1and 2]. Also, it is a secondary area of artificial intelligence (AI) in the computer science domain. It is believed that the roots of natural language processing can be traced to the article by Alan Turing titled ‘Computing machinery and intelligence’ [3]. The Turing test became known as the measure for a machine’s capacity to display intelligence. Noam Chomsky, recognized by academics and scientists as one of the founders of modern linguistics, then followed with his ‘Syntactic structures for grammar’ [4]. Acknowledged as the most significant text in the linguistics domain, it came to be accepted as the basic hypothesis for natural language processing. Chomsky’s syntactic structure is utilized in a substantial number of machine translation systems. Machine translation, automatic summarization, information retrieval, optical character recognition, speech recognition, and text-to-speech conversion are among the operations that can be carried out by way of NLP. Depending on the nature of an operation, NLP schemes are employed for the management of issues that include natural language understanding, natural language generation, speech and text segmentation, part-of-speech tagging and word sense disambiguation [1, 5]. Machine translation (MT), which is a field of NLP, can be employed for the translation of speech or text in a source language (SL) into the target language (TL). The emphasis of MT schemes is on the provision of an optimal translation devoid of any human intervention. A wide range of instruments for the translation of text from one dialect to another is available on the internet. While some of these instruments rely on the linguistic details of the source and target languages (machine translation systems that are rule-based), others focus on mathematical probabilities (machine translation systems based on statistics) for the execution of the translation process. However, the accuracy of MT systems is reduced when it comes to identifying complete phrases and their closest matching segments in the target language [6]. Among the approaches employed by the many currently available MT systems are the human-assisted, rule-based, statistical, example-based, hybrid, and agent- based methods. Included in the list of acclaimed machine translation systems are Anusaaraka, Google translator and SYSTRAN. The phases for the machine translation process are portrayed in Figure-1.