Virtual humans are computer-generated characters designed to look and behave like real people. Studies have shown that virtual humans can mimic many of the social effects that one finds in human-human interactions such as creating rapport, and people respond to virtual humans in ways that are similar to how they respond to real people. We believe that virtual humans represent a new metaphor for interacting with computers, one in which working with a computer becomes much like interacting with a person and this can bring social elements to the interaction that are not easily supported with conventional interfaces. We present two systems that embody these ideas. The first, the Twins are virtual docents in the Museum of Science, Boston, designed to engage visitors and raise their awareness and knowledge of science. The second SimCoach, uses an empathetic virtual human to provide veterans and their families with information about PTSD and depression.

We take a conversational character trained on a set of linked question-answer pairs authored by hand, and augment its training data by adding sets of question-answer pairs which are generated automatically from texts on different topics. The augmented characters can answer questions about the new topics, at the cost of some performance loss on questions about the topics that the original character was trained to answer.

See Leuski et al. (2006) and to the same question -- for example, "What Leuski and Traum (2008) for more details. is your name?" -- depending on who the interactor The final parameter is the classification threshold is looking at. NPCEditor's user interface allows the on the KL-divergence value: only answers that designer to define arbitrary annotation classes or score above the threshold value are returned from categories and specify which of these annotation the classifier. The threshold is determined by tuning categories should be used in classification.

Augmenting word tokens with a phonetic representation, derived from a dictionary, improves the performance of a Natural Language Understanding component that interprets speech recognizer output: we observed a 5% to 7% reduction in errors across a wide range of response return rates. The best performance comes from mixture models incorporating both word and phone features. Since the phonetic representation is derived from a dictionary, the method can be applied easily without the need for integration with a specific speech recognizer. The method has similarities with autonomous (or bottom-up) psychological models of lexical access, where contextual information is not integrated at the stage of auditory perception but rather later.

NPCEditor is a system for building a natural language processing component for virtual humans capable of engaging a user in spoken dialog on a limited domain. It uses a statistical language classification technology for mapping from user's text input to system responses. NPCEditor provides a user-friendly editor for creating effective virtual humans quickly. It has been deployed as a part of various virtual human systems in several applications.

This article describes the virtual humans developed as part of the Mission Rehearsal Exercise project, a virtual reality-based training system. This project is an ambitious exercise in integration, both in the sense of integrating technology with entertainment industry content, but also in that we have joined a number of component technologies that have not been integrated before. This integration has not only raised new research issues, but it has also suggested some new approaches to difficult problems. We describe the key capabilities of the virtual humans, including task representation and reasoning, natural language dialogue, and emotion reasoning, and show how these capabilities are integrated to provide more human-level intelligence than would otherwise be possible.

This article describes the virtual humans developed as part of the Mission Rehearsal Exercise project, a virtual reality-based training system. This project is an ambitious exercise in integration, both in the sense of integrating technology with entertainment industry content, but also in that we have joined a number of component technologies that have not been integrated before. This integration has not only raised new research issues, but it has also suggested some new approaches to difficult problems. We describe the key capabilities of the virtual humans, including task representation and reasoning, natural language dialogue, and emotion reasoning, and show how these capabilities are integrated to provide more human-level intelligence than would otherwise be possible.

The 1999 Association for the Advancement of Artificial Intelligence Fall Symposium Series was held Friday through Sunday, 5-7 November 1999, at the Sea Crest Oceanfront Resort and Conference Center. The titles of the five symposia were (1) Modal and Temporal Logics-Based Planning for Open Networked Multimedia Systems; (2) Narrative Intelligence; (3) Psychological Models of Communication in Collaborative Systems; (4) Question-Answering Systems; and (5) Using Layout for the Generation, Understanding, or Retrieval of Documents.

We order its events and find meaning in them by assimilating them to more or less familiar narratives. Temporal A wide variety of systems were presented: 1999, at the Sea Crest Oceanfront and modal logics have been used to story generation, interactive Resort and Conference Center. The reason about time, action, and adaptive fiction (including the first public titles of the five symposia were change and to program and verify demonstration from Joseph Bates's networked systems. How can we create characters from specifications of service quality in which interactive narrative emerges? The symposium focused mainly on a single, comprehensive theoretical framework, Clark's grounding model.

The Association for the Advancement of Artificial Intelligence held its 1997 Fall Symposia Series on 7 to 9 November in Cambridge, Massachusetts. This article contains summaries of the six symposia that were conducted: (1) Communicative Action in Humans and Machines, (2) Context in Knowledge Representation and Natural Language, (3) Intelligent Tutoring System Authoring Tools, (4) Model-Directed Autonomous Systems, (5) Reasoning with Diagrammatic Representations II, and (6) Socially Intelligent Agents.