We present a new system, called Cirrin, for pen input of ASCII characters using word-level unistrokes. Our system addresses the tradeoff between speed and accuracy of penbased tex...
Abstract. We address the problems of pattern matching and approximate pattern matching in the sketching model. We show that it is impossible to compress the text into a small sketc...
Ziv Bar-Yossef, T. S. Jayram, Robert Krauthgamer, ...
This work presents improvements of a large-scale Arabic to French statistical machine translation system over a period of three years. The development includes better preprocessin...
This paper describes an architecture to convert Sinhala Unicode text into phonemic specification of pronunciation. The study was mainly focused on disambiguating schwa-/\/ and /a/...
This paper discusses the interpretation of nominalizations in domain independent wide-coverage text. We present a statistical model which interprets nominalizations based on the c...