This paper addresses the challenging problem of learning from multiple annotators whose labeling accuracy (reliability) differs and varies over time. We propose a framework based ...
This paper presents a video acquisition system that can learn automatic video capture from human's camera operations. Unlike a predefined camera control system, this system c...
Scientific data offers some of the most interesting challenges in data integration today. Scientific fields evolve rapidly and accumulate masses of observational and experiment...
Partha Pratim Talukdar, Zachary G. Ives, Fernando ...
Multi-category classification of short dialogues is a common task performed by humans. When assigning a question to an expert, a customer service operator tries to classify the cu...
Conversations provide rich opportunities for interactive, continuous learning. When something goes wrong, a system can ask for clarification, rewording, or otherwise redirect the...