We develop, analyze, and evaluate a novel, supervised, specific-to-general learner for a simple temporal logic and use the resulting algorithm to learn visual event definitions fr...
We present a technique which complements Hidden Markov Models by incorporating some lexicalized states representing syntactically uncommon words. 'Our approach examines the d...
This paper addresses the problem of extending an adaptive information filtering system to make decisions about the novelty and redundancy of relevant documents. It argues that rel...
We present a general methodology for extracting multi-word expressions (of various types), along with their translations, from small parallel corpora. We automatically align the p...
In this paper, we investigate using meeting-specific characteristics to improve extractive meeting summarization, in particular, speaker-related attributes (such as verboseness, g...