Machine Translation: Goals, Issues, Approaches, and Applications
The world of computers has so far been dominated by English but, with the advent of the World Wide Web, this is becoming less true by the day. It has been predicted that by 2005 more than 50% of information available through the web will not be in English.
Machine translation (MT) is one of the oldest areas of Artificial Intelligence. It has had its up and downs but interest is currently at an all-time high and large strides have been made in improving the quality of translation, to the point where many organizations find it useful to use MT to provide at least a first pass at translating into or from a foreign language. Several translation engines (of highly variable quality) are also available on the web for the casual user and a multitude of personal software can be bought for little money.
In this talk I will review briefly the field of MT, describe several approaches that have been developed over the years, and discuss their strong points and weaknesses. I will also consider different applications of MT and the quality requirements of each application. The goal is to give the audience a broad overview of the field of MT and its current status. Time permitting, I will also describe in some detail specific research and development projects that I have been involved in.
Violetta Cavalli-Sforza is an Assistant Professor of Computer Science at San Francisco State University. She received her B.S. and M.S. in Civil Engineering, Infrastructure Planning and Management from Stanford University in 1980, her M.S. in Computer Science from Stanford in 1985, and her Ph.D. in Intelligent Systems from the University of Pittsburgh in 1998. She worked at Symantec in the early 1980Us, at Digital Equipment CorporationUs System Research Center (1985-88), at Carnegie Mellon University's Department of Philosophy (1988-89) and Center for Machine Translation (1994-99), and at Carnegie Technology Education (1999-2000). Her research interests include interlingua- and example-based machine translation, computational morphology (especially of Arabic), and intelligent computer-assisted language learning. She is the recipient of a National Science Foundation international fellowship and a Fulbright fellowship for work on machine translation between Arabic and English and Arabic and French in Morocco (2001 - 2005).