The present research examined two alternative interpretations of violation-of-expectation findings that young infants can represent hidden objects. One interpretation is that, when watching an event in which an object becomes hidden behind another object, infants form a prediction about the event's outcome while both objects are still visible, and then check whether this prediction was accurate...

Text interpretation involves several component tasks, including parsing, word-sense disambiguation and semantic relation assignment. To combine these tasks, the pipeline architecture has been widely used. Components for each task are connected serially and each one passes a single solution to the next component in line. This architecture, however, has a serious disadvantage that can significant...

Behaviour recognition in a video scene consists of several distinct sub-tasks: objects or object parts must be recognised, classified and tracked, qualitative spatial and temporal properties must be determined, behaviour of individual objects must be identified, and composite behaviours must be determined to obtain an interpretation of the scene as a whole. In this paper, we describe how these ...

........................................................................................................................................................ i Acknowledgements ....................................................................................................................................iii Contributions...............................................................................

One interpretation of levels of processing effects (LOP) on priming in implicit tests of memory is in terms of deficits in lexical processing during shallow study tasks. In two experiments the extent of lexical processing engaged in during standard shallow encoding tasks was manipulated by placing the encoding question either before or after the target stimulus. Clear evidence was found in expl...

Previous research has shown that people use linguistic distributional information during conceptual processing, and that it is especially useful for shallow tasks and rapid responding. Using two conceptual combination tasks, we showed that this linguistic shortcut extends to the processing of novel stimuli, is used in both successful and unsuccessful conceptual processing, and is evident in bot...

Introduction A central scientific goal of image understanding research is to investigate ways of bringing diverse sources of knowledge to bear on the problem of interpreting images. An important source of knowledge used by humans in the interpretation of aerial photographs is the topographic map. This paper describes some initial experiments in the use of map knowledge to automate an important ...

The goal of our research is to develop agents that can learn new tasks through real-time natural interactions with a human. Previously, we have described Rosie, an agent implemented in Soar that interactively learns new tasks. In this paper, we describe novel extensions to Rosie that allow it to learn complex, hierarchically defined concepts and to dynamically compile the interpretation of the ...