Contribution to Book
A Discriminative Model for Perceptually-Grounded Incremental Reference ResolutionProceedings of ICWS 2015 (2015)
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.
EditorMatthew Purver, Mehrnoosh Sadrzadeh, and Matthew Stone
PublisherAssociation for Computational Linguistics
Citation InformationCasey Kennington, Livia Dia and David Schlangen. "A Discriminative Model for Perceptually-Grounded Incremental Reference Resolution" London, UKProceedings of ICWS 2015 (2015) p. 195 - 205
Available at: http://works.bepress.com/casey-kennington/4/