Search this site

Guide to PROMT Machine Translation

What is Machine Translation (MT)?

Machine translation is the technology for translation of texts of all sorts from one natural language to another automatically, without human intervention. Machine translation technology is based on the in-depth research in the field of linguistics and Natural Language Processing and the application of innovative computer technologies to the task of translating texts from one natural language to another. One of the earliest pursuits in computer science, MT has proved to be an elusive goal, but today a number of systems is available which produce an output which, if not perfect, is of sufficient quality to be useful in a number of specific domains.
 
Systems for automatic translation have been under development for 50 years - in fact, ever since the electronic computer was invented in the 1940s there has been research on their application for foreign language translations. For many years, the systems were based primarily on direct translations via bilingual dictionaries, with relatively little detailed analysis of syntactic structures. By the 1980s, however advances in computational linguistics allowed much more sophisticated approaches, and a number of systems adopted an indirect approach to the task of translation. In these systems, texts of the source language are analyzed into abstract representations of 'meaning', involving successive programs for identifying word structure (morphology) and sentence structure (syntax) and for resolving problems of ambiguity.
 
The abstract representations are intended to be unambiguous and to provide the basis for the generation of texts into one or more target languages. There have in fact been two basic 'indirect' approaches. In one approach, based on the 'interlingua' principle the abstract representation is designed to be a kind of language-independent 'interlingua', which can potentially serve as an intermediary between a large number of natural languages. Translation is therefore in two basic stages: from the source language into the interlingua and from the interlingua into the target language. In the other, more common indirect approach (based on the 'transfer' principle) the representation is converted first into an equivalent representation for the target language. Thus there are three basic stages: analysis of the input text into an abstract source representation, transfer to an abstract target representation, and generation into the output language.
 
Until the late 1980s, systems of all these kinds were developed, and it is true to say that all current commercially available systems are also classifiable into these three basic system types: direct, interlingual and 'transfer'. The best known of the MT systems for mainframe computers are in fact essentially of the 'transfer translation' type and PROMT systems also perform the translation of 'transfer' type. PROMT translation systems are however improved versions of the type, unlike their predecessors, they are highly modular in construction and easily modifiable and extendable.