![]() |
![]() |
University of Birmingham > Talks@bham > Artificial Intelligence and Natural Computation seminars > Talking about Space
Talking about SpaceAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Lars Kunze. Host: Dr. Nick Hawes In recent years a range of technical developments in speech recognition and sensors have led to increased application of dialogue interfaces to computational systems that can sense the world around them. Examples of this type of system include robotic systems and smart phones. From a language research perspective an interesting aspect of these systems is that the dialog interface needs to be able to accommodate spatial descriptions. For example, a user might request a robot to ‘get the book that is on the shelf near the table’, or to ‘take the next turn right and go along the corridor until you are at the green door’. Although using and interpreting these spatial descriptions are second nature to humans, modelling the semantics of descriptions computationally turns out to be surprisingly complex. This talk will provide an overview of some of the linguistic and psycholinguistic findings related to spatial language and a review of different computational models that have been developed to capture the semantics of these terms. Speaker’s homepage: http://www.comp.dit.ie/jkelleher/ This talk is part of the Artificial Intelligence and Natural Computation seminars series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsComputer Science Departmental Series Biosciences seminars Data Science and Computational Statistics SeminarOther talksModelling uncertainty in image analysis. When less is more - reduced physics simulations of the solar wind The development of an optically pumped magnetometer based MEG system Provably Convergent Plug-and-Play Quasi-Newton Methods for Imaging Inverse Problems Perfect matchings in random sparsifications of Dirac hypergraphs Ultrafast, all-optical, and highly efficient imaging of molecular chirality |