Perceptual interpretation and the transformation of events into language

This thesis describes the principles underlying PIXEL (for Perceptual Interpretation and the Trans(X)formation of Events into Language), a system that uses focus of attention in generating and learning natural language descriptions of event perceptions. PIXEL identifies the salient features of events through cooperation between processes that are perceptually bottom-up and linguistically top-down. As events are perceived, data-driven attention guides event schemata generation, prediction, and selection. Through interaction with a human informant, goal-driven attention abstracts perceptual semantics and lexicalizes selected event schemata to generate an interpretation space for verbalization.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Electrical Engineering

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2011

Author dc:creator

• Maddox, Anthony Bernard

Contributors dc:contributor

• Waltz, David L.

• Engineering, Electronics and Electrical
• Computer Science

Statement dc:rights

• Copyright 1989 Maddox, Anthony Bernard

Language dc:language

eng

Identifier

AAI8924890
(UMI)AAI8924890

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/19232