When building a new spoken dialogue application, large amounts of domain specific data are required. This paper addresses the issue of generating in-domain training data when litt...
Few systems combine both Embodied Conversational Agents (ECAs) and multimodal input. This research aims at modeling the behavior of adults and children during their multimodal int...
Packrat parsing is a novel technique for implementing parsers in a lazy functional programming language. A packrat parser provides the power and flexibility of top-down parsing wi...
Byzantine Quorum Systems is a replication technique used to ensure availability and consistency of replicates data even in presence of arbitrary faults. This paper presents a Byzan...
To leverage large-scale weakly-tagged images for computer vision tasks (such as object detection and scene recognition), a novel cross-modal tag cleansing and junk image filtering...