Persistent Link:
http://hdl.handle.net/10150/203490
Title:
A Framework for Recognizing and Executing Verb Phrases
Author:
Hewlett, Daniel Krishnan
Issue Date:
2011
Publisher:
The University of Arizona.
Rights:
Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
Abstract:
Today, the physical capabilities of robots enable them to perform a wide variety of useful tasks for humans, making the need for simple and intuitive interaction between humans and robots readily apparent. Taking natural language as a key element of this interaction, we present a novel framework that enables robots to learn qualitative models of the semantics of an important class of verb phrases, such as "follow me to the kitchen," and leverage these verb models to perform two tasks: Executing verb phrase commands, and recognizing when another agent has performed a given verb. This framework is based on a qualitative, relational model of verb semantics called the Verb Finite State Machine, or VFSM. We describe the VFSM in detail, motivating its design and providing a characterization of the class of verbs it can represent. The VFSM supports the recognition task natively, and we show how to combine it with modern planning techniques to support verb execution in complex environments. Grounded natural language semantics must be learned through interaction with humans, so we describe methods from learning VFSM verb models through natural interaction with a human teacher in the apprenticeship learning paradigm. To demonstrate the efficacy of our framework, we present empirical results showing rapid learning and high performance on both the recognition and execution tasks. In these experiments, the VFSM is able to consistently outperform a baseline method based on recent work in the verb learning literature. We close with a discussion of some of the current limitations of the framework, and a roadmap for future work in this area.
Type:
text; Electronic Dissertation
Keywords:
Computer Science
Degree Name:
Ph.D.
Degree Level:
doctoral
Degree Program:
Graduate College; Computer Science
Degree Grantor:
University of Arizona
Advisor:
Cohen, Paul R.

Full metadata record

DC FieldValue Language
dc.language.isoenen_US
dc.titleA Framework for Recognizing and Executing Verb Phrasesen_US
dc.creatorHewlett, Daniel Krishnanen_US
dc.contributor.authorHewlett, Daniel Krishnanen_US
dc.date.issued2011-
dc.publisherThe University of Arizona.en_US
dc.rightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.en_US
dc.description.abstractToday, the physical capabilities of robots enable them to perform a wide variety of useful tasks for humans, making the need for simple and intuitive interaction between humans and robots readily apparent. Taking natural language as a key element of this interaction, we present a novel framework that enables robots to learn qualitative models of the semantics of an important class of verb phrases, such as "follow me to the kitchen," and leverage these verb models to perform two tasks: Executing verb phrase commands, and recognizing when another agent has performed a given verb. This framework is based on a qualitative, relational model of verb semantics called the Verb Finite State Machine, or VFSM. We describe the VFSM in detail, motivating its design and providing a characterization of the class of verbs it can represent. The VFSM supports the recognition task natively, and we show how to combine it with modern planning techniques to support verb execution in complex environments. Grounded natural language semantics must be learned through interaction with humans, so we describe methods from learning VFSM verb models through natural interaction with a human teacher in the apprenticeship learning paradigm. To demonstrate the efficacy of our framework, we present empirical results showing rapid learning and high performance on both the recognition and execution tasks. In these experiments, the VFSM is able to consistently outperform a baseline method based on recent work in the verb learning literature. We close with a discussion of some of the current limitations of the framework, and a roadmap for future work in this area.en_US
dc.typetexten_US
dc.typeElectronic Dissertationen_US
dc.subjectComputer Scienceen_US
thesis.degree.namePh.D.en_US
thesis.degree.leveldoctoralen_US
thesis.degree.disciplineGraduate Collegeen_US
thesis.degree.disciplineComputer Scienceen_US
thesis.degree.grantorUniversity of Arizonaen_US
dc.contributor.advisorCohen, Paul R.en_US
dc.contributor.committeememberMorrison, Clayton T.en_US
dc.contributor.committeememberFasel, Ianen_US
dc.contributor.committeememberCohen, Paul R.en_US
This item is licensed under a Creative Commons License
Creative Commons
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.