“Show me the cup”: reference with continuous representations

Home | About RECERCAT | Contact

Català | Castellano

All of RECERCAT

By Communities &
Collections By Defense Date By Authors By Titles By Subject

This Collection

By Defense Date By Authors By Titles By Subject

Statistics

View Statistics All RECERCAT

My RECERCAT

Other repositories directory

RECERCAT Home > Universitat Pompeu Fabra > Articles, congressos, llibres > View document

To access the full text documents, please follow this link: http://hdl.handle.net/10230/32700

dc.contributor.author	Boleda, Gemma
dc.contributor.author	Baroni, Marco
dc.contributor.author	Padó, Sebastian
dc.date	2018
dc.identifier.citation	Baroni M, Boleda G, Padó S. “Show me the cup”: reference with continuous representations. In: Gelbukh A, editor. Computational linguistics and intelligent text processing: 18th International Conference, CICLing 2017 revised selected papers, part 1; 2017 Apr 17-23; Budapest, Hungary. Cham: Springer; 2018. p. 209-24.
dc.identifier.uri	http://hdl.handle.net/10230/32700
dc.format	application/pdf
dc.language.iso	eng
dc.publisher	Springer
dc.relation	Gelbukh A, editor. Computational linguistics and intelligent text processing: 18th International Conference, CICLing 2017 revised selected papers, part 1; 2017 Apr 17-23; Budapest, Hungary. Cham: Springer; 2018. p. 209-24.
dc.relation	info:eu-repo/grantAgreement/EC/H2020/655577
dc.relation	info:eu-repo/grantAgreement/EC/H2020/715154
dc.relation	info:eu-repo/grantAgreement/ES/1PE/FFI2013-41301-P
dc.relation	info:eu-repo/grantAgreement/EC/FP7/283554
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	Reference
dc.subject	Semantics
dc.subject	Computational semantics
dc.subject	Distributed representations
dc.subject	Computational Linguistics
dc.subject	Natural Language Processing
dc.title	“Show me the cup”: reference with continuous representations
dc.type	info:eu-repo/semantics/conferenceObject
dc.type	info:eu-repo/semantics/acceptedVersion
dc.description.abstract	Comunicació presentada a CICLing 2017, celebrat a Budapest (Hongria) del 17 al 23 d'abril de 2017.
dc.description.abstract	One of the most basic functions of language is to refer to objects in a shared scene. Modeling reference with continuous representations is challenging because it requires individuation, i.e., tracking and distinguishing an arbitrary number of referents. We introduce a neural network model that, given a de nite description and a set of objects represented by natural images, points to the intended object if the expression has a unique referent, or indicates a failure, if it does not. The model, directly trained on reference acts, is competitive with a pipeline manually engineered to perform the same task, both when referents are purely visual, and when they are characterized by a combination of visual and linguistic properties.
dc.description.abstract	This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 655577 (LOVe) and ERC grant agreement No 715154 (AMORE); ERC 2011 Starting Independent Research Grant n. 283554 (COMPOSES); DFG (SFB 732, Project D10); and Spanish MINECO (grant FFI2013-41301-P).

Show simple item record

All of RECERCAT

This Collection

Statistics

My RECERCAT

Related documents

Other documents of the same author