|
The Georgetown-IBM experiment was an influential demonstration of machine translation, which was performed during January 7, 1954. Developed jointly by the Georgetown University and IBM, the experiment involved completely automatic translation of more than sixty Russian sentences into English. ==Background== Conceived and performed primarily in order to attract governmental and public interest and funding by showing the possibilities of machine translation, it was by no means a fully featured system: It had only six grammar rules and 250 lexical items in its vocabulary (of stems and endings). This complete dictionary was never fully shown (only the extended one from Garvin's article). Apart from general topics, the system was specialised in the domain of organic chemistry. The translation was done using an IBM 701 mainframe computer (launched in April 1953). Sentences had to be punched onto cards. George-IBM experiment is the most known result of the MIT conference in June 1952 where were invited the all active researchers in mechanical translation field. Duncan Harkin from US Department of Defense suggested there that his department would finance a new mechanical translation project. Jerome Weisner supported the idea and offered finance from the Research Laboratory of Elecronics at MIT. Leon Dostert had been invited to the project for his previous experience with automatic corrections of translations (back then 'mechanical translation'), high impact had his interpretation system for Nuremberg War Crimes Tribunal. The linguistics part of the demonstration was mostly done by linguist Paul Garvin who had also good knowledge of Russian. Over 60 Romanized Russian statements regarding a wide range of political, legal, mathematic, and scientific subjects were entered into the machine by a computer operator who knew no Russian, and the resulting English translations appeared on a printer. The translated sentences were attentivelly chosen. Many operations of the demonstration were fitted to specific words and sentences. There wasn't also present any relational or sentence analysis which could recognize the phase structure. The approach was mostly 'lexicographic' based on dictionary where specific word had a connection with a specific rules and steps. 抄文引用元・出典: フリー百科事典『 ウィキペディア（Wikipedia）』 ■ウィキペディアで「Georgetown-IBM experiment」の詳細全文を読む スポンサード リンク
|