Font Size: a A A

Research On Tracking And Memorizing Mechanism In Human-Machine Interactive Hybrid Strategies Machine Translation System (IHSMTS)

Posted on:2001-07-22Degree:DoctorType:Dissertation
Country:ChinaCandidate:C L HuFull Text:PDF
GTID:1118360185495646Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
With the growth of international communication and Internet, the language barrier is becoming a serious problem. The grown-up of Machine Translation (MT) brings a good chance to solve this difficulty. It has taken on great significance in academic research and good prospect in applications as diverse as: translation of business letters and reports; translation of technical documents and articles; and speech-to-speech translation for business and travel. It has become one of the international drastic competing areas of high technology.Until now, MT has developed for nearly half a century. During these five decades, all kinds of application MT systems, such as on-line, domain-restricted and machine-aided translation, have come forth to accommodate information processing and network developing. But from the point of view of a great deal of demand and the low quality of translation, these systems are far from practicality and have such problems as: 1) The quality of direct MT translation is so low that human has to do heavy and difficult work after that. 2) Machine can not collect experiences and not enhance the power of himself, so always makes the same mistakes.IHSMT system has just been designed to solve the above problems. It forms a nice interdependent cooperation relation between human and machine by interaction, which not only helps solve the inherent problems of MT, but also makes feedback learning possible. At the same time, IHSMTS achieves hybrid...
Keywords/Search Tags:learning model of HMTM, human-machine interaction, hybrid strategies MT, matching analogy, case-based reasoning
PDF Full Text Request
Related items