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...
Components allow to design applications in a modular way by enforcing a strong separation of concerns. In distributed systems this separation of concerns have to be composed with ...
Learning patterns of human behavior from sensor data is extremely important for high-level activity inference. We show how to extract a person’s activities and significant plac...
Real-life systems are usually hard to control, due to their complicated structures, quantitative time factors and even stochastic behaviors. In this work, we present a model checke...
Songzheng Song, Jun Sun 0001, Yang Liu 0003, Jin S...
Abstract: We study an instance-based approach for matching hierarchical ontologies, such as product catalogs. The motivation for utilizing instances is that metadata-based match ap...