Natural language understanding is central to the goals of artificial intelligence. Any truly intelligent machine must be capable of carrying on a conversation: dialogue, particularly clarification dialogue, is essential if we are to avoid disasters caused by the misunderstanding of the intelligent interactive systems of the future. This book is an interim report on the grand enterprise of devising a machine that can use natural language as fluently as a human. What has really been achieved since this goal was first formulated in Turing’s famous test? What obstacles still need to be overcome?
Table of Contents
1. Knowledge Interactions and Integrated Parsing for Narrative Comprehension Michael G. Dyer 1.1. Introduction 1.2. Foundations in Comprehension 1.3. Multiple Knowledge Sources in BORIS 1.4. Generalizing Scripts with Multiple Perspectives 1.5. Processes of Comprehension 1.6. Memory Modification During Question Answering 1.7. Theory of Affect 1.8. Thematic Abstraction Units 1.9. Future Research 1.10. Conclusions 2. Event Concept Coherence Richard Alterman 2.1. Introduction 2.2. How NEXUS Works 2.3. In the Context of Some Other Representation Schemes 2.4. Summary and Conclusions 3. Learning Word Meanings From Examples Robert C. Berwick 3.1. Introduction 3.2. The Acquisition Procedure 3.3. Implementation and Examples 3.4. Learning Nouns and Class Hierarchies 3.5. Conclusions 4. An Introduction to Plot Units Wendy G. Lehnert and Cynthia L. Loiselle 4.1. Understanding and Representation 4.2. The Plot Unit Representational System 4.3. Summarization from Plot Units 4.4. Evidence for the Psychological Validity of Plot Units 4.5. An Overall View 5. Natural Language Description of Time-Varying Scenes Bernd Neumann 5.1. Overview 5.2. Representing the Scheme 5.3. Events 5.4. Verbalization 5.5. Composing a Description 5.6. Discussion