Search |  Contact |  SRI Home Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap.A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A ASRI International.  333 Ravenswood Avenue.  Menlo Park, CA 94025-3493. SRI International is a nonprofit corporation.

AIC Seminar Series

Socially Aware Inference: A Landmark on the Path to Human-Level Dialog

Will BridewellStanford Center for Biomedical Informatics Research[Home Page]

Notice:  Hosted by Richard Waldinger.

Date:  2012-04-26 at 16:00

Location:  EJ228 (SRI E building)  (Directions)

   Abstract

NOTE: download slides and video of the talk from the two links below (the one labeled "Document" is a video).

From ELIZA to Siri, human-level dialog has been a holy grail for intelligent systems for several decades. Success will require a re-envisioning of the solution: an approach that views dialog in terms of social cognition as opposed to simple pattern matches and state transitions. In this talk, I will detail a new strategy, motivated by the need for an interactive medical expert, that combines abductive reasoning with agent models to produce a socially aware inference system. I will also present recent findings and insights about knowledge structures, representation, and inference mechanisms, linking these to the next stages of the research program.

This talk will describe joint research with Amar K. Das, Pat Langley (ASU/ISLE), Nicholas L. Cassimatis (RPI), Sergei Nirenberg (UMBC), and Jerry Hobbs (USC) on the Unified Theories of Language and Cognition project sponsored through the Office of Naval Research.

   Bio for Will Bridewell

Will Bridewell is a research scientist at the Stanford Center for Biomedical Informatics Research (BMIR). He earned his PhD in Computer Science in 2004 from the University of Pittsburgh, where he developed a simple method for detecting negation in medical records and a unique approach to explaining anomalies in scientific data. Afterwards, he moved to the Computational Learning Laboratory at Stanford University, where he furthered research in inductive process modeling and other forms of computational scientific discovery. He joined BMIR in 2009 to develop a thrilling new approach to abductive inference that would form the foundations of a system that supports socially aware inference.

   On-line Resources