Please use this identifier to cite or link to this item:
Title: The role of graduality for referring expression generation in visual scenes
Authors: Gatt, Albert
Marin, Nicolas
Portet, Francois
Sanchez, Daniel
Keywords: Reference (Linguistics)
Natural language processing (Computer science)
Linguistic analysis (Linguistics)
Word (Linguistics)
Typology (Linguistics)
Issue Date: 2016
Publisher: Springer International Publishing
Citation: Gatt, A., Marín, N., Portet, F., & Sánchez, D. (2016). The role of graduality for referring expression generation in visual scenes. International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, Eindhoven. 191-203.
Abstract: Referring Expression Generation (reg) algorithms, a core component of systems that generate text from non-linguistic data, seek to identify domain objects using natural language descriptions. While reg has often been applied to visual domains, very few approaches deal with the problem of fuzziness and gradation. This paper discusses these problems and how they can be accommodated to achieve a more realistic view of the task of referring to objects in visual scenes.
Appears in Collections:Scholarly Works - InsLin

Files in This Item:
File Description SizeFormat 
ipmu2016_gradable-reg.pdf396.69 kBAdobe PDFView/Open

Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.