The Association for the Advancement of Artificial Intelligence (AAAI) held its 1997 Spring Symposium Series on 24 to 26 March at Stanford University in Stanford, California. This article contains summaries of the seven symposia that were conducted: (1) Artificial Intelligence in Knowledge Management; (2) Computational Models for Mixed-Initiative Interaction; (3) Cross-Language Text and Speech Retrieval; (4) Intelligent Integration and Use of Text, Image, Video, and Audio Corpora; (5) Natural Language Processing for the World Wide Web; (6) Ontological Engineering; and (7) Qualitative Preferences in Deliberation and Practical Reasoning.

The Association for the Advancement of Artificial Intelligence (AAAI) held its 1997 Spring Symposium Series on 24 to 26 March at Stanford University in Stanford, California. This article contains summaries of the seven symposia that were conducted: (1) Artificial Intelligence in Knowledge Management; (2) Computational Models for Mixed-Initiative Interaction; (3) Cross-Language Text and Speech Retrieval; (4) Intelligent Integration and Use of Text, Image, Video, and Audio Corpora; (5) Natural Language Processing for the World Wide Web; (6) Ontological Engineering; and (7) Qualitative Preferences in Deliberation and Practical Reasoning.

The next portion of the workshop was devoted to different approaches to preventing and repairing miscommunication. These sessions represent a progression between different parts of their discourse Research related to achieving from work that clarifies the model or between the discourse robust interaction is an important problem of miscommunication to model and the domain model. Early work concerned work that describes the strategies The last session was the presentation the correction of spelling or grammatical used to repair miscommunication. I of work involving deployed systems errors in a user's utterance so review the most significant issues using speech as a mode of interaction. The approaches were constrained by their have assumed that the system's model differed in two dimensions: First, experimenters impact on overall system performance is always correct.