Tom Williams, Matthias Scheutz
The Oxford Handbook of Reference
As robots become increasingly prevalent in our society, it becomes increasingly important to endow them with natural language capabilities, including the ability to both understand and generate so-called referring expressions. In recent, work, we have sought to enable referring expression understanding capabilities by leveraging the Givenness Hierarchy (GH), which provides an elegant linguistic framework for reasoning about notions of reference in human discourse. In this chapter, we first provide an overview of the GH and discuss previous GH-theoretic approaches to reference resolution. We then describe our own GH-theoretic approach, the GH-POWER algorithm, and suggest future refinements of our algorithm with respect to the theoretical commitments of the GH. Next, we briefly survey other prominent approaches to reference resolution in robotics, and discuss how these compare to our approach. Finally, we conclude with a discussion of possible directions for future work.