In the talk I am going to discuss the problem of understanding the connections between human activities and the content of textual information generated in regard to those activities. I'm going to describe our experiments on the domain of massive online collaborative environments, specifically online virtual worlds or massive online multiplayer games. In these virtual worlds people meet, chat to each other, and do things together. We study how well we can detect, explain, and predict the people activities in the virtual world from the content of their chat messages. I'm going to present some initial results that show how statistical language modeling and text clustering techniques may allow us to explore those chat-to-action connections successfully.
Dr. Anton Leuski is a Research Scientist at the Institute for Creative Technologies with the University of Southern California. He completed his Ph.D. in Computer Science at the University of Massachusetts at Amherst in 2001. His research interests center around interactive information access, human-computer interaction, and machine learning. Dr. Leuski's recent work has focused on natural language problems that facilitate dialog between humans and virtual characters, specifically language understanding and classification, natural language generation, and activity detection and tracking in massive collaborative environments.
This talk is part of the CLIP Colloquium Series, organized by Jimmy Lin (jimmylin -at- umd .dot. edu). For the complete schedule, please visit http://www.umiacs.umd.edu/research/CLIP/colloq/.