Unifying language modeling capabilities for flexible interaction

Dialogue processing has taken several different forms in recent years; in this paper we address a cognitive modeling approach to the problem. We begin by sketching some of our work in this area and how it derives from prior research in cognition, modeling, nat-ural language processing, and discourse recipe compilation. We then note that, whereas the complexities of natural language— especially spoken language—have been primarily addressed by technologies that target lower-level linguistic processing, higher-level processing has been less well studied. We introduce our ap-proach, which is to use an agent-based cognitive modeling archi-tecture for dialogue processing. We mention some of the advan-tages to using such a framework for dialogue, particularly the per-spicuity of a unified architecture. We then explore the difficulties and challenges of using a cognitive modeling foundation. Partic