Referring under Uncertainty

Marín Ruiz, Nicolás; Rivas Gervilla, Gustavo; Sánchez Fernández, Daniel

doi:10.1109/FUZZ-IEEE.2019.8859027

referringUnderUncertainty_DIGIBUG.pdf (414.9Kb)

Identificadores

URI: https://hdl.handle.net/10481/111038

DOI: 10.1109/FUZZ-IEEE.2019.8859027

ISBN: 9781538617281

Exportar

Editorial

IEEE

Materia

referring expression

uncertainty

referential success

possibility theory

Fecha

2019

Referencia bibliográfica

Published version: N. Marín, G. Rivas-Gervilla and D. Sánchez, "Referring under Uncertainty," 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), New Orleans, LA, USA, 2019, pp. 1-6, doi: 10.1109/FUZZ-IEEE.2019.8859027

Patrocinador

Spanish Ministry of Education, Culture and Sports FPU16/05199; Spanish Government TIN2014-58227-P, PGC2018-096156-B-I00; Fondo Europeo de Desarrollo Regional - FEDER

Resumen

In this paper, we study the referring expression generation problem (REG) when the available information about the properties of objects is uncertain, in the sense that we are not sure about the actual properties an object has. We formalize the problem by extending the conventional REG framework through the use of possibility distributions, represented by fuzzy sets. We show the potential benefits of this proposal in the assessment of the referential success for referring expressions. This approach opens a new line of research in the application of fuzzy sets to the REG problem, complementary to those approaches that use fuzzy sets as a suitable bridge between language and raw data.

Colecciones

DCCIA - Comunicaciones Congresos, Conferencias, ...

Excepto si se señala otra cosa, la licencia del ítem se describe como Attribution-NonCommercial-NoDerivatives 4.0 Internacional