date: 2019-11-12T05:15:41Z
pdf:docinfo:custom:lastpage: 13165
pdf:PDFVersion: 1.3
pdf:docinfo:title: Modeling Conceptual Understanding in Image Reference Games
access_permission:can_print_degraded: true
EventType: Poster
pdf:docinfo:custom:firstpage: 13155
subject: Neural Information Processing Systems http://nips.cc/
dc:format: application/pdf; version=1.3
access_permission:fill_in_form: true
pdf:encrypted: false
dc:title: Modeling Conceptual Understanding in Image Reference Games
Book: Advances in Neural Information Processing Systems 32
pdf:docinfo:custom:Date: 2019
modified: 2019-11-12T05:15:41Z
Description-Abstract: An agent who interacts with a wide population of other agents needs to be aware that there may be variations in their understanding of the world. 
Furthermore, the machinery which they use to perceive may be inherently different, as is the case between humans and machines.
In this work, we present both an image reference game between a speaker and a population of listeners where reasoning about the concepts other agents can comprehend is necessary and a model formulation with this capability. 
We focus on reasoning about the conceptual understanding of others, as well as adapting to novel gameplay partners and dealing with differences in perceptual machinery. 
Our experiments on three benchmark image/attribute datasets suggest that our learner indeed encodes information directly pertaining to the understanding of other agents, and that leveraging this information is crucial for maximizing gameplay performance.
cp:subject: Neural Information Processing Systems http://nips.cc/
pdf:docinfo:subject: Neural Information Processing Systems http://nips.cc/
pdf:docinfo:custom:Created: 2019
pdf:docinfo:creator: Rodolfo Corona Rodriguez, Stephan Alaniz, Zeynep Akata
meta:author: Rodolfo Corona Rodriguez, Stephan Alaniz, Zeynep Akata
access_permission:extract_for_accessibility: true
lastpage: 13165
pdf:docinfo:custom:Type: Conference Proceedings
Editors: H. Wallach and H. Larochelle and A. Beygelzimer and F. d'Alché-Buc and E. Fox and R. Garnett
Author: Rodolfo Corona Rodriguez, Stephan Alaniz, Zeynep Akata
producer: PyPDF2
pdf:docinfo:producer: PyPDF2
pdf:docinfo:custom:Description: Paper accepted and presented at the Neural Information Processing Systems Conference (http://nips.cc/)
pdf:unmappedUnicodeCharsPerPage: 0
Description: Paper accepted and presented at the Neural Information Processing Systems Conference (http://nips.cc/)
access_permission:modify_annotations: true
firstpage: 13155
dc:creator: Rodolfo Corona Rodriguez, Stephan Alaniz, Zeynep Akata
pdf:docinfo:custom:EventType: Poster
Last-Modified: 2019-11-12T05:15:41Z
dcterms:modified: 2019-11-12T05:15:41Z
title: Modeling Conceptual Understanding in Image Reference Games
Last-Save-Date: 2019-11-12T05:15:41Z
Created: 2019
pdf:docinfo:modified: 2019-11-12T05:15:41Z
Language: en-US
pdf:docinfo:custom:Language: en-US
pdf:docinfo:custom:Book: Advances in Neural Information Processing Systems 32
meta:save-date: 2019-11-12T05:15:41Z
Content-Type: application/pdf
X-Parsed-By: org.apache.tika.parser.DefaultParser
creator: Rodolfo Corona Rodriguez, Stephan Alaniz, Zeynep Akata
access_permission:assemble_document: true
xmpTPg:NPages: 11
Publisher: Curran Associates, Inc.
pdf:charsPerPage: 2955
access_permission:extract_content: true
Date: 2019
access_permission:can_print: true
Type: Conference Proceedings
pdf:docinfo:custom:Editors: H. Wallach and H. Larochelle and A. Beygelzimer and F. d'Alché-Buc and E. Fox and R. Garnett
pdf:docinfo:custom:Description-Abstract: An agent who interacts with a wide population of other agents needs to be aware that there may be variations in their understanding of the world. 
Furthermore, the machinery which they use to perceive may be inherently different, as is the case between humans and machines.
In this work, we present both an image reference game between a speaker and a population of listeners where reasoning about the concepts other agents can comprehend is necessary and a model formulation with this capability. 
We focus on reasoning about the conceptual understanding of others, as well as adapting to novel gameplay partners and dealing with differences in perceptual machinery. 
Our experiments on three benchmark image/attribute datasets suggest that our learner indeed encodes information directly pertaining to the understanding of other agents, and that leveraging this information is crucial for maximizing gameplay performance.
pdf:docinfo:custom:Published: 2019
Published: 2019
pdf:docinfo:custom:Publisher: Curran Associates, Inc.
access_permission:can_modify: true