A Discriminative Model for Perceptually-Grounded Incremental Reference Resolution

Kennington C, Dia L, Schlangen D (2015)
In: Proceedings of the 11th International Conference on Computational Semantics (IWCS) 2015. 195-205.

Download
OA
Conference Paper | Published | English
Abstract
A large part of human communication involves referring to entities in the world, and often these entities are objects that are visually present for the interlocutors. A computer system that aims to resolve such references needs to tackle a complex task: objects and their visual features must be determined, the referring expressions must be recognised, extra-linguistic information such as eye gaze or pointing gestures must be incorporated --- and the intended connection between words and world must be reconstructed. In this paper, we introduce a discriminative model of reference resolution that processes incrementally (i.e., word for word), is perceptually-grounded, and improves when interpolated with information from gaze and pointing gestures. We evaluated our model and found that it performed robustly in a realistic reference resolution task, when compared to a generative model.
Publishing Year
Conference
International Conference on Computational Semantics (IWCS) 2015
Location
London
Conference Date
2015-04-15 – 2015-04-17
PUB-ID

Cite this

Kennington C, Dia L, Schlangen D. A Discriminative Model for Perceptually-Grounded Incremental Reference Resolution. In: Proceedings of the 11th International Conference on Computational Semantics (IWCS) 2015. 2015: 195-205.
Kennington, C., Dia, L., & Schlangen, D. (2015). A Discriminative Model for Perceptually-Grounded Incremental Reference Resolution. Proceedings of the 11th International Conference on Computational Semantics (IWCS) 2015, 195-205.
Kennington, C., Dia, L., and Schlangen, D. (2015). “A Discriminative Model for Perceptually-Grounded Incremental Reference Resolution” in Proceedings of the 11th International Conference on Computational Semantics (IWCS) 2015 195-205.
Kennington, C., Dia, L., & Schlangen, D., 2015. A Discriminative Model for Perceptually-Grounded Incremental Reference Resolution. In Proceedings of the 11th International Conference on Computational Semantics (IWCS) 2015. pp. 195-205.
C. Kennington, L. Dia, and D. Schlangen, “A Discriminative Model for Perceptually-Grounded Incremental Reference Resolution”, Proceedings of the 11th International Conference on Computational Semantics (IWCS) 2015, 2015, pp.195-205.
Kennington, C., Dia, L., Schlangen, D.: A Discriminative Model for Perceptually-Grounded Incremental Reference Resolution. Proceedings of the 11th International Conference on Computational Semantics (IWCS) 2015. p. 195-205. (2015).
Kennington, Casey, Dia, Livia, and Schlangen, David. “A Discriminative Model for Perceptually-Grounded Incremental Reference Resolution”. Proceedings of the 11th International Conference on Computational Semantics (IWCS) 2015. 2015. 195-205.
Main File(s)
File Name
Access Level
OA Open Access
Last Uploaded
2016-09-16T05:46:49Z

This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar