Anticipating the availability of large questionanswer datasets, we propose a principled, datadriven Instance-Based approach to Question Answering. Most question answering systems ...
We propose a new approach for learning Bayesian classifiers from data. Although it relies on traditional Bayesian network (BN) learning algorithms, the effectiveness of our approa...
This paper uses Factored Latent Analysis (FLA) to learn a factorized, segmental representation for observations of tracked objects over time. Factored Latent Analysis is latent cl...
Labeling persons appearing in video frames with names detected from the video transcript helps improving the video content identification and search task. We develop a face naming...
Phi The Pham, Marie-Francine Moens, Tinne Tuytelaa...
Pseudo-likelihood and contrastive divergence are two well-known examples of contrastive methods. These algorithms trade off the probability of the correct label with the probabili...