Specificity measures and reference
Abstract
In this paper we study empirically the validity of measures of referential success for referring expressions involving gradual properties. More specifically, we study the ability of several measures of referential success to predict the success of a user in choosing the right object, given a referring expression. Experimental results indicate that certain fuzzy measures of success are able to predict human accuracy in reference resolution. Such measures are therefore suitable for the estimation of the success or otherwise of a referring expression produced by a generation algorithm, especially in case the properties in a domain cannot be assumed to have crisp denotations.
Keywords
Cite
@article{arxiv.1810.00333,
title = {Specificity measures and reference},
author = {Albert Gatt and Nicolás Marín and Gustavo Rivas-Gervilla and Daniel Sánchez},
journal= {arXiv preprint arXiv:1810.00333},
year = {2018}
}
Comments
Accepted for publication in: Proceedings of the 11th International Conference on Natural Language Generation. Tilburg, The Netherlands: Association for Computational Linguistics 11 pages, 5 figures, 6 tables