Development of a Machine Traustation System or the Basis of "Meanig From Theory"

Research Project

Project/Area Number	07808039
Research Category	Grant-in-Aid for Scientific Research (C)
Allocation Type	Single-year Grants
Section	一般
Research Field	Intelligent informatics
Research Institution	Osaka University
Principal Investigator	HOSOYA Yukiteru Osaka University, Faculty Language and Culture, assistant professor, 言語文化部, 助教授 (90116096)
Project Period (FY)	1995 – 1996
Project Status	Completed (Fiscal Year 1996)
Budget Amount *help	¥2,100,000 (Direct Cost: ¥2,100,000) Fiscal Year 1996: ¥800,000 (Direct Cost: ¥800,000) Fiscal Year 1995: ¥1,300,000 (Direct Cost: ¥1,300,000)
Keywords	Machine Translation / Meaning From Theory / Translation / 意味形態
Research Abstract	Though the pioneers of "machine translation" put in a lot of effort, the results have not been up to the demands of practical usage. The reason appears to be that linguistic findings have not been used sufficiently, especially those in the field of the semantics of translation. From a practical point of view it is impossible to create good machine translation without programming the techniques and linguistic intuition of qualified translators. So far I have been mainly concerned with the analysis of translation techniques and linguistic intuitions of German native speakers by using the "meaning from theory" as virtually the only method for analysis of linguistic intuition. I applied the results of these investigations to this project, "Development of a machine translation system on the basis of 'meaning form theory'" and achieved a better translation system. To mention a technical result from the project, I have developed a "point sorting" technique by which it is possible to list German words including the German special characters (e.g. "Umlaut" ) in alphabetical order. The best way to assess the quality of my machine translation system is to run the software I developed for this system.