Approach to Machine Translation

Way to Evaluate

1. Feasibility evaluation
Evaluation dedicated to assess the success possibility of approach in machine translation. There are some characteristic of evaluations, one of which is to adapt with work circumstance through the modification or function broaden

2. Internal Evaluation
Evaluation which is aimed to exam is the component of MT prototype can work with the aim appropriately. This evaluation is done continuously and periodically in the time of research and development.

3. Diagnostic Evaluation
Evaluation which is aimed to find the MT system causes which cannot give the expected result.

4. Declarative Evaluation
Evaluation which is aimed to measure the MT ability in translating text correctly. The source that is evaluated is coming from the output text linguistic phenomenon which seems from two crucial characteristics that is intelligibility (the grade of the target language text), and fidelity (the accuracy and complexity of the information transferred from source language to the target language).

5. Operational Evaluation
Evaluation which is to know the MT program has worked as the operational of its context. This evaluation is the most complex evaluation, it is done in the real MT use circumstance.

Machine Translation

History of Machine Translation

The translation of natural languages by machine, first dreamt of in the seventeenth century, has become a reality in the late twentieth. Computer programs are producing translations - not perfect translations, for that is an ideal to which no human translator can aspire; nor translations of literary texts, for the subtleties and nuances of poetry are beyond computational analysis; but translations of technical manuals, scientific documents, commercial prospectuses, administrative memoranda, medical reports. Machine translation is not primarily an area of abstract intellectual inquiry but the application of computer and language sciences to the development of systems answering practical needs.

Basic Features and Terminology

A. Definition
The term 'machine translation' (MT) refers to computerized systems responsible for the production of translations with or without human assistance. It is the application of computers to the task of translating texts from one natural language to another. This machine excludes computer-based translation tools which support translators by providing access to on-line dictionaries, remote terminology databanks, transmission and reception of texts, etc.