Hidden Markov Models (HMMs) are one of the most fundamental and widely used statistical tools for modeling discrete time series. In general, learning HMMs from data is computation...
A spoken language generation system has been developed that learns to describe objects in computer-generated visual scenes. The system is trained by a `show-and-tell' procedu...
A serious bottleneck in the development of trainable text summarization systems is the shortage of training data. Constructing such data is a very tedious task, especially because...
This paper reports on how we learned from an alternative practice, to design engaging interactive technology intended for a more general user group. We are investigating new types ...
Clustering by document concepts is a powerful way of retrieving information from a large number of documents. This task in general does not make any assumption on the data distrib...