We describe a method for the fully automatic learning of hierarchical finite state translation models. The input to the method is transcribed speech utterances and their correspon...
We describe a method for finding ungapped conserved words in rRNA sequences that is effective, utilizes evolutionary information and does not depend on multiple sequence alignment...
Liaofu Luo, Li-Ching Hsieh, Fengmin Ji, Mengwen Ji...
In this paper a new and efficient supervised method for color image segmentation is presented. This method improves a part of the automatic extraction problem. The basic technique...
The output of handwritten word recognizers (WR) tends to be very noisy due to various factors. In order to compensate for this behaviour, several choices of the WR must be initial...
This paper describes a new statistical parser which is based on probabilities of dependencies between head-words in the parse tree. Standard bigram probability estimation techniqu...