Abstract. We have been working on the integration of video with supplementary documents, such as cooking programs. We propose an integration system that performs semantic segmentat...
This paper describes a new representation for the audio and visual information in a video signal. We reduce the dimensionality of the signals with singular-value decompositions (S...
One of the major problems one is faced with when decomposing words into their constituent parts is ambiguity: the generation of multiple analyses for one input word, many of which...
In recent work we have presented a formal framework for linguistic annotation based on labeled acyclic digraphs. These `annotation graphs' oer a simple yet powerful method fo...
We show how features can easily be added to standard generative models for unsupervised learning, without requiring complex new training methods. In particular, each component mul...
Taylor Berg-Kirkpatrick, Alexandre Bouchard-C&ocir...