Deep Learning for Category-Free Grounded Language Acquisition
dc.contributor.author | Pillai, Nisha | |
dc.contributor.author | Ferraro, Francis | |
dc.contributor.author | Matuszek, Cynthia | |
dc.date.accessioned | 2019-07-09T14:31:56Z | |
dc.date.available | 2019-07-09T14:31:56Z | |
dc.date.issued | 2019-06 | |
dc.description | NAACL Workshop on Spatial Language Understanding & Grounded Communication for Robotics. | en_US |
dc.description.abstract | We 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.uri | http://iral.cs.umbc.edu/Pubs/PillaiNAACLws2019.pdf | en_US |
dc.format.extent | 11 pages | en_US |
dc.genre | conference papers and proceedings preprints | en_US |
dc.identifier | doi:10.13016/m2nngg-xn9e | |
dc.identifier.citation | Nisha 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.pdf | en_US |
dc.identifier.uri | http://hdl.handle.net/11603/14358 | |
dc.language.iso | en_US | en_US |
dc.publisher | Association for Computational Linguistics (ACL) | |
dc.relation.isAvailableAt | The University of Maryland, Baltimore County (UMBC) | |
dc.relation.ispartof | UMBC Computer Science and Electrical Engineering Department Collection | |
dc.relation.ispartof | UMBC Faculty Collection | |
dc.relation.ispartof | UMBC Student Collection | |
dc.rights | This 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.subject | deep learning | en_US |
dc.subject | grounding acquisition system | en_US |
dc.subject | logistic regression classifier | en_US |
dc.subject | Interactive Robotics and Language Lab | |
dc.subject | language | |
dc.title | Deep Learning for Category-Free Grounded Language Acquisition | en_US |
dc.type | Text | en_US |