Perceptual interpretation and the transformation of events into language
Maddox, Anthony Bernard
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/19232
Description
Title
Perceptual interpretation and the transformation of events into language
Author(s)
Maddox, Anthony Bernard
Issue Date
1989
Doctoral Committee Chair(s)
Waltz, David L.
Department of Study
Electrical and Computer Engineering
Discipline
Electrical Engineering
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Engineering, Electronics and Electrical
Computer Science
Language
eng
Abstract
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.
PIXEL characterizes three aspects of visuolinguistic conceptualization. First, it demonstrates how attention during observation selects perceptual features for event conceptualization. Second, PIXEL suggests how perceptual meaning may be derived through dialogue to guide the mapping of linguistic representations of events into generalized event concepts. Finally, it illustrates that data-driven and goal-driven attention can combine to facilitate learning under perceptual or linguistic control.
The domain of this research is a space station in low-earth orbit. In particular, the problem of real-time communication between astronauts and teleoperated robotic servicing systems that assist in assembly, maintenance, and inspection tasks is addressed.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
