Deep Learning for Category-Free Grounded Language Acquisition

Simple item page
dc.contributor.authorPillai, Nisha
dc.contributor.authorFerraro, Francis
dc.contributor.authorMatuszek, Cynthia
dc.date.accessioned2019-07-09T14:31:56Z
dc.date.available2019-07-09T14:31:56Z
dc.date.issued2019-06
dc.descriptionNAACL Workshop on Spatial Language Understanding & Grounded Communication for Robotics.en_US
dc.description.abstractWe propose a learning system in which language is grounded in visual percepts without pre-defined category constraints. We present a unified generative method to acquire a shared semantic/visual embedding that enables a more general language grounding acquisition system. We evaluate the efficacy of this learning by predicting the semantics of ground truth objects and comparing the performance with each of a predefined category classifier and a simple logistic regression classifier. Our preliminary results suggest that this generative approach exhibits promising results in language grounding without pre-specifying visual categories such as color and shape.en_US
dc.description.urihttp://iral.cs.umbc.edu/Pubs/PillaiNAACLws2019.pdfen_US
dc.format.extent11 pagesen_US
dc.genreconference papers and proceedings preprintsen_US
dc.identifierdoi:10.13016/m2nngg-xn9e
dc.identifier.citationNisha Pillai , et.al, Deep Learning for Category-Free Grounded Language Acquisition, NAACL-SpLU-RoboNLP, Minneapolis, Minnesota, June 2019, http://iral.cs.umbc.edu/Pubs/PillaiNAACLws2019.pdfen_US
dc.identifier.urihttp://hdl.handle.net/11603/14358
dc.language.isoen_USen_US
dc.publisherAssociation for Computational Linguistics (ACL)
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.relation.ispartofUMBC Student Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
dc.subjectdeep learningen_US
dc.subjectgrounding acquisition systemen_US
dc.subjectlogistic regression classifieren_US
dc.subjectInteractive Robotics and Language Lab
dc.subjectlanguage
dc.titleDeep Learning for Category-Free Grounded Language Acquisitionen_US
dc.typeTexten_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
PillaiNAACLws2019.pdf
Size:
1.94 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection