Generating Quantified Referring Expressions with Perceptual Cost Pruning

Gordon Briggs, Hillary Harner


Abstract
We model the production of quantified referring expressions (QREs) that identify collections of visual items. To address this task, we propose a method of perceptual cost pruning, which consists of two steps: (1) determine what subset of quantity information can be perceived given a time limit t, and (2) apply a preference order based REG algorithm (e.g., the Incremental Algorithm) to this reduced set of information. We demonstrate that this method successfully improves the human-likeness of the IA in the QRE generation task and successfully models human-generated language in most cases.
Anthology ID:
W19-8602
Volume:
Proceedings of the 12th International Conference on Natural Language Generation
Month:
October–November
Year:
2019
Address:
Tokyo, Japan
Editors:
Kees van Deemter, Chenghua Lin, Hiroya Takamura
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
11–18
Language:
URL:
https://aclanthology.org/W19-8602
DOI:
10.18653/v1/W19-8602
Bibkey:
Cite (ACL):
Gordon Briggs and Hillary Harner. 2019. Generating Quantified Referring Expressions with Perceptual Cost Pruning. In Proceedings of the 12th International Conference on Natural Language Generation, pages 11–18, Tokyo, Japan. Association for Computational Linguistics.
Cite (Informal):
Generating Quantified Referring Expressions with Perceptual Cost Pruning (Briggs & Harner, INLG 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-8602.pdf