Events Calendar
Mar 28
17:00 - 18:30
Session on Artificial Intelligence
Centre for Language and Linguistics Invited Talk

Prof Alessandro Vinciarelli (University of Glasgow)Title: An introduction to Social Signal ProcessingAbstract: The goal of this talk is to introduce Social Signal Processing (SSP), the computing domain aimed at modelling, analysis and synthesis of nonverbal behaviour in human-human and human-machine interactions. The main methodological steps characterising Social Signal Processing approaches will be described through an example application, i.e., the automatic analysis of conflict in  political debates. Furthermore, the talk will show that the goal of Social Signal Processing approaches is not only to deal automatically with social and technological phenomena, but also to provide scientific insight about the way people use nonverbal communication in their interactions.

Dr Shoaib Jameel (University of Kent)Title: Entity Embeddings with Conceptual Subspaces as a Basis for Plausible Reasoning Abstract: Conceptual spaces are geometric representations of conceptual knowledge in which entities correspond to points, natural properties correspond to convex regions, and the dimensions of the space correspond to salient features. While conceptual spaces enable elegant models of various cognitive phenomena, the lack of automated methods for constructing such representations have so far limited their application in artificial intelligence. To address this issue, I present a method which learns a vector-space embedding of entities from Wikipedia and constrains this embedding such that entities of the same semantic type are located in some lower-dimensional subspace. Experiments demonstrate the usefulness of these subspaces as approximate conceptual space representations by showing, among others, that important features can be modelled as directions and that natural properties tend to correspond to convex regions.

Location

Lecture Theatre 1,
Darwin College,
University of Kent,
Canterbury,
Kent,
CT2 7NY
United Kingdom
Map

Details

Open to all,

Contact: Dr Eleni Kapogianni
E: E.Kapogianni@kent.ac.uk

 

Corporate Communications - © University of Kent

The University of Kent, Canterbury, Kent, CT2 7NZ, T: +44 1227 764000

Last Updated: 10/01/2012