Automatic referent resolution of deictic and anaphoric expressions

Deictic and anaphoric expressions frequently cause problems for natural language analysis. In this paper we present a single model that accounts for referent resolution of deictic and anaphoric expressions in a research prototype of a multimodal user interface called EDWARD. The linguistic expressions are keyed in by a user and are possibly accompanied by pointing gestures. The proposed model for reference resolution elaborates on Alshawi's (1987) notions of context factors and salience and integrates both linguistic and perceptual context effects. The model is contrasted with two alternative referent resolution models, namely, a simplistic one and the more sophisticated model proposed by Grosz and Sidner (1986). Based on empirical and analytical grounds, we conclude that the model we propose is preferable from a computational and engineering point of view.