A Knowledge-Based Machine Translation Using AI Technique

A Knowledge-Based Machine Translation Using AI Technique

Sahar A. El-Rahman (Benha University, Cairo, Egypt & Princess Nourah Bint Abdulrahman University, Riyadh, Saudi Arabia), Tarek A. El-Shishtawy (Benha University, Banha, Egypt) and Raafat A. El-Kammar (Benha University, Banha, Egypt)
Copyright: © 2018 |Pages: 14
DOI: 10.4018/IJSI.2018070106
OnDemand PDF Download:
List Price: $37.50
10% Discount:-$3.75


This article presents a realistic technique for the machine aided translation system. In this technique, the system dictionary is partitioned into a multi-module structure for fast retrieval of Arabic features of English words. Each module is accessed through an interface that includes the necessary morphological rules, which directs the search toward the proper sub-dictionary. Another factor that aids fast retrieval of Arabic features of words is the prediction of the word category, and accesses its sub-dictionary to retrieve the corresponding attributes. The system consists of three main parts, which are the source language analysis, the transfer rules between source language (English) and target language (Arabic), and the generation of the target language. The proposed system is able to translate, some negative forms, demonstrations, and conjunctions, and also adjust nouns, verbs, and adjectives according their attributes. Then, it adds the symptom of Arabic words to generate a correct sentence.
Article Preview

2. Approaches To Machine Translation

Historically, the strategies for Machine Aided Translation fall into the following categories (Hutchins & Somers, 1992):

2.1. Direct Approach

The translation system was reduced to word-for word substitution (El-Hamayed, 1992). The direct approach works best when the two languages are both lexically and structurally similar.

2.2. Indirect Approach (Thunes, 1993)

It can be summarized as:

  • Interlingua approach (Blekhman, Kursin, & Fagradiants, 1998; Bel et al., 1999): Source text --[analysis]-- Interlingua --[synthesis]-- Target text

  • Transfer approach (Gimenez & Forcada, 1998; El-Shishtawy, 1997) Source text –[analysis]—Intermediate Structure (source) –[transfer]—Intermediate Structure (target) –[synthesis]—Target text

2.3. Knowledge-Based Approach

There is a fairly new approach called knowledge-based machine translation (KBMT) (Carbonell Cullingford, & Gershman, 1981). Successful translation by machine requires the use of various types of knowledge (hence the term ”Knowledge Based Machine Translation”) for each language (Leavit, Londale, & Franz, 1994). This includes spelling, contraction, and formatting rules; morphological rules; lexical knowledge, including syntactic features, semantic concepts, collocation and terminological information; knowledge about grammatical structure; and semantic rules (Elkateb & Black, 2001; El-Azim, 1994).

Complete Article List

Search this Journal:
Volume 11: 1 Issue (2023): Forthcoming, Available for Pre-Order
Volume 10: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 9: 4 Issues (2021)
Volume 8: 4 Issues (2020)
Volume 7: 4 Issues (2019)
Volume 6: 4 Issues (2018)
Volume 5: 4 Issues (2017)
Volume 4: 4 Issues (2016)
Volume 3: 4 Issues (2015)
Volume 2: 4 Issues (2014)
Volume 1: 4 Issues (2013)
View Complete Journal Contents Listing