Santa Fe Institute

Groups

Barbara Grosz

Science Board

Higgins Professor of Natural Sciences, Harvard University, School of Engineering and Applied Sciences

Curriculum Vitae

Bio

Artificial Intelligence Collaborative Planning and Human-Computer Communication

One of the major challenges for computer science in the next decade is to create the scientific and technological base for easy-to-use, large-scale information systems. Better systems for human-computer communication are an essential part of this challenge. Theories and models of collaboration are important to this endeavor as well as to providing the foundations for constructing systems able to work with each other and their users. The ability to collaborate is critical if we are to have systems that are helpful assistants and not merely tools.

Professor Grosz's research group is addressing fundamental problems in modeling collaborative activity, developing systems ("agents") able to collaborate with each other and their users, and constructing collaborative, multi-modal systems for human-computer communication. Professor Grosz is also attempting to identify the basic structures and processes by which people use natural languages to communicate, focusing in particular on the mechanisms involved in dialogue and spontaneous speech.

Because collaborative action comprises actions by different agents, collaborative planning and activity involve the intentions of multiple agents. The collaborative planning process is a refinement process: a partial plan description is modified over the course of planning by the multiple participants involved in the collaboration. The SharedPlans model of collaboration (developed in collaboration with S. Kraus) handles multiple levels of action decomposition and is comprehensive in its treatment of partiality of belief and intention. Professor Grosz's research group is extending this model and using it in developing intelligent computer "agents" that work together in teams.

Professor Grosz has developed a theory of discourse structure that specifies how discourse interpretation depends on interactions among speaker intentions, attentional state, and linguistic form. Her current research in discourse processing has two foci. First, with colleagues at AT&T Bell Laboratories, she is using the theory to study the information about discourse structure conveyed by intonation, i.e., how tones demark, in spoken language, some of the structure that paragraphs and parentheses indicate in written language. Applications of this work should lead to better computer speech-synthesis systems. Second, she is involved in an interdisciplinary investigation of the connections between centering of attention and form of reference.

These two strands of research are being combined in an effort (joint with Professor Stuart Shieber) that aims to provide the scientific and technological base for a new paradigm for human-computer interaction, one that would enable the principled design of multi-modal dialogue-supporting interfaces. This research is investigating ways in which a theoretical understanding of collaborative activity can inform in a principled manner the design of concrete software interfaces. As a first step in this direction, Professor Grosz's research group has developed the DIAL system, a collaborative web interface for distance learning.