Automated Machine Reading

Professors:David Israel
Credits:2.5
Range:B
Note:

Full description

Automated Machine Reading

by

David Israel (SRI, USA) 

(also part of Seminars in Artificial Intelligence and Robotics fo MSc)

 

Abstract: The course will present the results developed within SRI's FAUST Project within DARPA's Machine Reading Program. The aim of the Program is to create automated reading systems that make the information in natural language texts accessible to a range of formal reasoning systems -- both deductive and probabilistic. The SRI-led FAUST team proposed an architecture based on statistical joint inference over probabilistic relational models. Supporting the simultaneous consideration of random variables enables the leveraging of all mutually constraining information and the integration of information across sentences and texts. This joint inference engine integrates information from more specialized inference modules, in particular, an ensemble of natural language modules. Such integration requires the coordination or alignment of representations from multiple levels of analysis and multiple texts. SRI is continually improving these alignments using machine learning techniques. This approach builds on significant recent advances in probabilistic representation and joint inference, and will enable the system to consider the widest range of both linguistic and extra-linguistic evidence, using the same mechanisms that are used for the integration of linguistic information across levels. 


Fridays 12:00-13:30 // 14:00-15:30, Room B2

May 9, 16, 23, 26, and 30, 2014

More information can be found at http://www.dis.uniroma1.it/~corsoai1/SAI/