The technology that is based on regular machine translation is the most mature, also be to apply so far the widest, at present influential machine translation system is based on regulation. The accidence that be based on regular machine translation system is antonym character statement, syntactic, semantics and syntax undertake analysis, judgement is mixed accept or reject, arrange combination afresh next, generate equivalent target language.

The method that is based on intermediate language is the expression that the generation after undertaking an analysis to source language becomes intermediate language one kind form, plant by this directly next the expression of intermediate language the form makes target language. Alleged the systematization that intermediate language represents a form with respect to the computer that is natural language, it tries to create give a kind of independence at all sorts of natural language, can represent the artificial language of all sorts of natural language again at the same time.

The machine translation that is based on regulation develops today, opposite for more mature already. Although pass long-term effort, people has been built contain by tens of thousands regular regular library, enclothed quite big language phenomenon, but from theoretic tell, this kind of process is very finite still. Because the language is a nation,pass a few chiliad accumulate, it is established by usage and of dynamic development. As ceaseless development of the society, new vocabulary and language phenomenon appear ceaselessly. The regulation of existing machine translation system is again much, also be specific language phenomenon only generalize and sum up. Accordingly, the machine translation method that is based on regulation drew lessons from the advantage of other method, produce a lot of change, basically reflect in the following respects:

In regulation get a respect, traditional regular method basically relies on linguist to sum up regulation to undertake debugging, and take seriously more now get regulation from inside the corpus (if use the study algorithm of wrong drive) ;

Traditional regular method often slants to describe thick granuality again, the knowledge of regulation of big range linguistics that overall situation changes, and take descriptive granule seriously to spend more now, the lingustic knowledge of local little scope, present the trend of ” of a library of “ little regulation, big dictionary;

The side shows in knowledge, to have a description to translating knowledge with more smaller size, accurate ground, should have nothing to do to pure context commonly regulation is done a few improve;

Traditional regular method uses often dispute this namely the determinism principle of those, rash club sex of the system is poorer, and multiform probability or grading function introduce commonly in regular now system, the gender raises rash baton of the system somewhat.
Previous12 Next