This paper describes a novel method by which a dialogue agent can learn to choose an optimal dialogue strategy. While it is widely agreed that dialogue strategies should be formulated in terms of communicative intentions, there has been little work on automatically optimizing an agent's choices when there are multiple ways to realize a communicative intention. Our method is based on a combinati...

Feedback utterances are among the most frequent in dialogue. Feedback is also a crucial aspect of all linguistic theories that take social interaction involving language into account. However, determining communicative functions is a notoriously difficult task both for human interpreters and systems. It involves an interpretative process that integrates various sources of information. Existing ...

The language/action perspective (LAP) as orginally introduced by Winograd and Flores has inspired several tools and information system design methodologies. The goal of this article is to make the communication norms underlying various LAP workflow loop models (DEMO, ActionWorkflow) explicit and to contrast them with the auditing norms of internal control. It appears that the communicative acti...

The overall goal of our research is a system which can recognize the intended message of a grouped bar chart by reasoning about the communicative signals contained in the graphic. One such communicative signal is the relative effort required to perform different perceptual tasks on the graphic. This paper presents our methodology for estimating relative task effort. Based on graph comprehension...

Any mechanism of language acquisition can only learn a restricted set of grammars. The human brain contains a mechanism for language acquisition which can learn a restricted set of grammars. The theory of this restricted set is universal grammar (UG). UG has to be sufficiently specific to induce linguistic coherence in a population. This phenomenon is known as "coherence threshold". Previously,...

An alternative theoretical framework for analyzing and designing computer-supported collaborative learning environments is introduced. Bateson’s theory (1973) is used as a starting point for considering in what sense the specific dialogical conditions and qualities of virtual environments may support learning. We need more stringent analytical approaches of research that relate communicative qu...

Recent years have seen a growing interest in creating virtual agents to populate the cast of characters for interactive narrative. A key challenge posed by interactive characters for narrative environments is devising expressive dialogue generators. To be effective, character dialogue generators must be able to simultaneously take into account multiple sources of information that bear on dialog...

The recent rise of Instant Messaging systems as a centerpiece of online communication has brought with it many questions about the role this new medium will play in the communicative sphere. As the medium has evolved, it has grown to subsume many traditional communication technologies, merging their individual capabilities. In this chapter, a cross-section of popular and established technologie...

Conversations are a useful means of structuring communicative interactions among agents. The value of a conversation-based approach is largely determined by the conversational model it uses. Finite State Machines, used heavily to date for this purpose, are not su cient for complex agent interactions requiring a notion of concurrency. We propose the use of Colored Petri Nets as a model underlyin...