In natural dialogues, speakers may make kinds of mistakes or so called irregular expressions. One of the most difficult porblems Dialogue Machien Translations must deal with is translating irregular expressins in the natural conversation, such as ungrammartic, uncompeleted, or ill-formed sentences. However most existing machien translation system reject utterances including irregular expressions. In this paper, we propose a Dialogue Machien translation uisng Multi-Processors(DMTMP) approach based on Cooperative Distributed natural language procesisng Model(CDM). In the DMTMP, several different type of mathods as following are used in origial language anlaysis and target language generation process simutanously.
展开▼