Referring Expression Generation under Uncertainty: Algorithm and Evaluation Framework

Tom Williams, Matthias Scheutz


Abstract
For situated agents to effectively engage in natural-language interactions with humans, they must be able to refer to entities such as people, locations, and objects. While classic referring expression generation (REG) algorithms like the Incremental Algorithm (IA) assume perfect, complete, and accessible knowledge of all referents, this is not always possible. In this work, we show how a previously presented consultant framework (which facilitates reference resolution when knowledge is uncertain, heterogeneous and distributed) can be used to extend the IA to produce DIST-PIA, a domain-independent algorithm for REG under uncertain, heterogeneous, and distributed knowledge. We also present a novel framework that can be used to evaluate such REG algorithms without conflating the performance of the algorithm with the performance of classifiers it employs.
Anthology ID:
W17-3511
Volume:
Proceedings of the 10th International Conference on Natural Language Generation
Month:
September
Year:
2017
Address:
Santiago de Compostela, Spain
Venues:
INLG | WS
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
75–84
Language:
URL:
https://www.aclweb.org/anthology/W17-3511
DOI:
10.18653/v1/W17-3511
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W17-3511.pdf