Barbara J. Grosz

Collaborative plans for complex group action

Abstract The original formulation of SharedPlans by B. Grosz and C. Sidner (1990) was developed to provide a model of collaborative planning in which it was not necessary for one agent to have intentions-to toward an act of a different agent. Unlike other contemporaneous approaches (J.R. Searle, 1990), this formulation provided for two agents to coordinate their activities without introducing any notion of irreducible joint intentions. However, it only treated activities that directly decomposed into single-agent actions, did not address the need for agents to commit to their joint activity, and did not adequately deal with agents having only partial knowledge of the way in which to perform an action. This paper provides a revised and expanded version of SharedPlans that addresses these shortcomings. It also reformulates Pollacks (1990) definition of individual plans to handle cases in which a single agent has only partial knowledge; this reformulation meshes with the definition of SharedPlans. The new definitions also allow for contracting out certain actions. The formalization that results has the features required by Bratmans (1992) account of shared cooperative activity and is more general than alternative accounts (H. Levesque et al., 1990; E. Sonenberg et al., 1992).

Pronouns, Names, and the Centering of Attention in Discourse

Centering theory, developed within computational linguistics, provides an account of ways in which patterns of interutterance reference can promote the local coherence of discourse. It states that each utterance in a coherent discourse segment contains a single semantic entity—the backward-looking center—that provides a link to the previous utterance, and an ordered set of entities—the forward-looking centers—that offer potential links to the next utterance. We report five reading-time experiments that test predictions of this theory with respect to the conditions under which it is preferable to realize (refer to) an entity using a pronoun rather than a repeated definite description or name. The experiments show that there is a single backward-looking center that is preferentially realized as a pronoun, and that the backward-looking center is typically realized as the grammatical subject of the utterance. They also provide evidence that there is a set of forward-looking centers that is ranked in terms of prominence, and that a key factor in determining prominence—surface-initial position—does not affect determination of the backward-looking center. This provides evidence for the dissociation of the coherence processes of looking backward and looking forward.

TEAM: an experiment in the design of transportable natural-language interfaces

Abstract This article describes TEAM, a transportable natural-language interface system. TEAM was constructed to test the feasibility of building a natural-language system that could be adapted to interface with new databases by users who are not experts in natural-language processing. An overview of the system design is presented, emphasizing those choices that were imposed by the demands of transportability. Several general problems of natural-language processing that were faced in constructing the system are discussed, including quantifier scoping, various pragmatic issues, and verb acquisition. TEAM is compared with several other transportable systems; this comparison includes a discussion of the range of natural language handled by each as well as a description of the approach taken to achieving transportability in each system.

PROVIDING A UNIFIED ACCOUNT OF DEFINITE NOUN PHRASES IN DISCOURSE

Citation Grosz, Barbara J., Aravind K. Joshi, and Scott Weinstein. 1983. Providing a unified account of definite noun phrases in discourse. In 21st Annual Meeting of the Association for Computational Linguistics: proceedings of the conference : 15-17 June 1983, Massachusetts Institute of Technology, Cambridge, Massachusetts, ed. Association for Computational Linguistics, 44-50. Morristown, N.J.: Association for Computational Linguistics.

The Evolution of Sharedplans

Rational agents often need to work together. There are jobs that cannot be done by one agent—for example, singing a duet or operating a computer network—and jobs that are more efficiently done by more than one agent—for example, hanging a door or searching the Internet. Collaborative behavior—coordinated activity in which the participants work jointly with each other to satisfy a shared goal—is more than the sum of individual acts [24, 8] and may be distinguished from both interaction and simple coordination in terms of the commitments agents make to each other [4, 10, 9]. A theory of collaboration must therefore treat not only the intentions, abilities, and knowledge about action of individual agents, but also their coordination in group planning and acting. It also must account for the ways in which plans are incrementally formed and executed by the participants.

A combinatorial auction for collaborative planning

When rational, utility-maximizing agents encounter an opportunity to collaborate on a group activity they must determine whether to commit to that activity. We refer to this problem as the initial-commitment decision problem (ICDP). The paper describes a mechanism that agents may use to solve the ICDP. The mechanism is based on a combinatorial auction in which agents bid on sets of roles in the group activity, each role comprising constituent subtasks that must be done by the same agent. Each bid may specify constraints on the execution times of the subtasks it covers. This mechanism permits agents to keep most details of their individual schedules of prior commitments private. The paper reports the results of several experiments testing the performance of the mechanism. These results demonstrate a significant improvement in performance when constituent subtasks are grouped into roles. They also show that as the number of time constraints in bids increases, the probability that there is a solution decreases, the cost of an optimal solution (if one exists) increases, and the time required to find an optimal solution (if one exists) decreases. The paper also describes several strategies that agents might employ when using this mechanism.

The Influence of Social Dependencies on Decision-Making: Initial Investigations with a New Game

This paper describes a new multi-player computer game, Colored Trails (CT), which may be played by people, computers and heterogeneous groups. CT was designed to enable investigation of properties of decision-making strategies in multi-agent situations of varying complexity. The paper presents the results of an initial series of experiments of CT games in which agentsý choices affected not only their own outcomes but also the outcomes of other agents. It compares the behavior of people with that of computer agents deploying a variety of decision-making strategies. The results align with behavioral economics studies in showing that people cooperate when they play and that factors of social dependency influence their levels of cooperation. Preliminary results indicate that people design agents to play strategies closer to game-theory predictions, yielding lower utility. Additional experiments show that such agents perform worse than agents designed to make choices that resemble human cooperative behavior. The paper describes challenges raised by these results for designers of agents, especially agents that need to operate in heterogeneous groups that include people.

Planning and Acting Together

People often act together with a shared purpose; they collaborate. Collaboration enables them to work more efficiently and to complete activities they could not accomplish individually. An increasing number of computer applications also require collaboration among various systems and people. Thus, a major challenge for AI researchers is to determine how to construct computer systems that are able to act effectively as partners in collaborative activity. Collaborative activity entails participants forming commitments to achieve the goals of the group activity and requires group decision making and group planning procedures. In addition, agents must be committed to supporting the activities of their fellow participants in support of the group activity. Furthermore, when conflicts arise (for example, from resource bounds), participants must weigh their commitments to various group activities against those for individual activities. This article briefly reviews the major features of one model of collaborative planning called SHARED-PLANS (Grosz and Kraus 1999, 1996). It describes several current efforts to develop collaborative planning agents and systems for human-computer communication based on this model. Finally, it discusses empirical research aimed at determining effective commitment strategies in the SHAREDPLANS context.

Socially conscious decision-making

For individually motivated agents to work collaboratively to satisfy shared goals, they must make decisions about actions and intentions that take into account their commitments to group activities. This paper examines the role of social consciousness in the process of reconciling intentions to do group-related actions with other, conflicting intentions. We operationalize the notion of social consciousness and provide a first attempt to formally add social consciousness to a cooperative decision-making model. We define a measure of social consciousness; describe its incorporation into the SPIRE experimental system, a simulation environment that allows the process of intention reconciliation in team contexts to be studied; and present results of several experiments that investigate the interaction in decision-making of measures of group and individual good. In particular, we investigate the effect of varying levels of social consciousness on the utility of the group and the individuals it comprises. A key finding is that an intermediate level of social consciousness yields better results in certain circumstances than an extreme commitment. We suggest preliminary principles for designers of collaborative agents based on the results.

Intonational features of local and global discourse structure

We present results of a study of the relationship between intonational features including pitch range, timing, and amplitude and aspects of discourse structure defined in terms of Grosz and Sidners (1986) model of discourse. We compare structural labelings of AP news text with prosodic/acoustic features examined from recordings of the same text read by a professional newscaster. We find significant correlations between prosodic/acoustic characteristics and both local and global aspects of discourse structure identified by our labelers. Our results have applications for speech synthesis and, potentially, for speech recognition.