Tracking Conversational Context for Machine Mediation of Human Discourse
作者： Alex Pentland , Tony Jebara , Yuri Ivanov , Ali Rahimi
DOI:
关键词: Class (computer programming) 、 Tracking (education) 、 Context (language use) 、 Computer science 、 Natural language processing 、 Artificial intelligence 、 Human–computer interaction 、 Conversation 、 Topic model 、 Mediation 、 Situation awareness 、 Group discussion
摘要: We describe a system that tracks conversational context using speech recognition and topic modeling. Topics are described by computing the frequency of words for each class. thus reliably detect, in real-time, currently active group discussion involving several individuals. One application this ’situational awareness’ is computer acts as mediator ofthe meeting, offering feedback relevant questions to stimulate further conversation. It also provides temporal analysis meeting’s evolution. demonstrate discuss other possible impacts situation awareness.
columbia.edu 参考文章(4)
Thad Starner, Bradley J. Rhodes, Remembrance Agent: A continuously running automated information retrieval system ,(1996)
Kamal Nigam, Andrew McCallum, A comparison of event models for naive bayes text classification national conference on artificial intelligence. pp. 41- 48 ,(1998)
T.S. Jebara, A. Pentland, Parametrized structure from motion for 3D adaptive feedback tracking of faces computer vision and pattern recognition. pp. 144- 150 ,(1997) , 10.1109/CVPR.1997.609312
David Franklin, Shannon Bradshaw, Kristian Hammond, Jabberwocky: you don't have to be a rocket scientist to change slides for a hydrogen combustion lecture intelligent user interfaces. pp. 98- 105 ,(2000) , 10.1145/325737.325792