Machine Translation of Noun Phrases: from English to Arabic

Abstract: The present work reports our attempt in developing a transfer-based machine translation system of English noun phrases into Arabic. English noun phrases are frequently used in scientific and technical documents. According to transfer approach of machine
translation, the system consists of three main modules, responsible for analysis, transfer, and generation. The analysis component assigns grammatical structures to the input noun phrase by means of English grammatical rules and an English monolingual dictionary. The transfer component builds target language equivalents of the source language grammatical structures by means of a comparative grammar that relates every source language representation to some corresponding target language representation. This involves a bilingual dictionary. The generation component provides the target language translation. This involves the synthesis grammar rules of Arabic and an Arabic monolingual dictionary.
A major design goal of this system is that it can be used as a
stand-alone tool and can be very well integrated with a general machine translation system for English sentence. The system is implemented in Prolog and the parser is written in DCG formalism. Experiment on real noun phrases was performed. The thesis also described our experience with the developed machine translation system and reports results of its application on real titles of thesis and journals.
URL
Publication year 2000
Organization Name
Author(s) from ARC
Agris Categories Documentation and information
Proposed Agrovoc Machiner Translation; noun phrase; transfer;
Publication Type Master Thesis