Multimodal Semantic Simulations of Linguistically Underspecified Motion Events
This work addresses the challenge of visualizing underspecified motion events for applications in natural language processing and computer graphics, but it appears incremental as it builds on existing semantic models.
The paper tackles the problem of generating 3D visual simulations from natural language motion expressions by using a formal model of events and semantic knowledge, resulting in a system that satisfies minimal linguistic constraints.
In this paper, we describe a system for generating three-dimensional visual simulations of natural language motion expressions. We use a rich formal model of events and their participants to generate simulations that satisfy the minimal constraints entailed by the associated utterance, relying on semantic knowledge of physical objects and motion events. This paper outlines technical considerations and discusses implementing the aforementioned semantic models into such a system.