Participating in explanatory dialogues: interpreting and responding to questions in context
Participating in explanatory dialogues: interpreting and responding to questions in context
The Psychology of Menu Selection: Designing Cognitive Control at the Human/Computer Interface
The Psychology of Menu Selection: Designing Cognitive Control at the Human/Computer Interface
Shadow: Fusing Hypertext with AI
IEEE Expert: Intelligent Systems and Their Applications
Controlling Content Realization with Functional Unification Grammars
Proceedings of the 6th International Workshop on Natural Language Generation: Aspects of Automated Natural Language Generation
Learning and remembering command names
CHI '82 Proceedings of the 1982 Conference on Human Factors in Computing Systems
Building Intelligent Interactive Tutors: Student-centered strategies for revolutionizing e-learning
Building Intelligent Interactive Tutors: Student-centered strategies for revolutionizing e-learning
| Hi-index | 4.10 |
Automatic text generators are at the heart of systems that provide users with information. The trick is getting the system to answer follow-up questions as naturally as possible. But even in moderately complex domains, the task of handcrafting explanations using "canned" text or templates is so time-consuming and error-prone that it becomes infeasible. Furthermore, these techniques cannot be extended to let a system consider the user's prior knowledge, past problem-solving experiences, or the preceding dialogue. To overcome these limitations, researchers have focused on automatically synthesizing text directly from underlying knowledge bases. Automatic text-generation systems pose new opportunities--and new problems. Studies of human-human interactions show that people often follow up requests for information with more questions. This observation also underscores the need for computer-based information systems to let users ask follow-up questions. This capability is especially crucial in patient education, for example, where misunderstandings could have serious consequences. The ability to handle follow-up requests in context is essential, even crucial, to applications like the patient education system described in this article. The direction we've taken presents one alternative to full-fledged natural language-understanding and makes it possible to design systems by adopting a pragmatic (and possibly more useful) approach of generating choices for the user. Our initial system evaluations reveal that users are comfortable with the interface as a way to ask follow-up questions.