Đang chuẩn bị liên kết để tải về tài liệu:
Báo cáo khoa học: "Knowledge Structures in UC, the UNIX* Consultant"

Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ

The knowledge structures implemented in UC, the UNLX Consultant are sufficient for UC to reply to a large range of user queries in the domain of the UNIX operating system. This paper describes how these knowledge structures are used in the natural language tasks of parsing, reference, planning, goal detection, and generation, and ~ow they are organized to enable efficient access even with the large database of an expert system. The structuring of knowledge to provide direct answers to common queries and the high usability and efficiency of knowledge structures allow UC to hold an interactive conversation with a. | Knowledge Structures in uc the UNIX Consultantf David N. Chin Division of Computer Science Department of EECS University of California Berkeley Berkeley CA. 04720 ABSTRACT The knowledge structures implemented in uc the UNIX Consultant are sufficient for uc to reply to a large range of user queries in the domain of the UNIX operating system. This paper describes how these knowledge structures are used in the natural language tasks of parsing inference planning goal detection and generation and how they are organized to enable efficient access even with the large database of an expert system. The structuring of knowledge to provide direct answers to common queries and the high usability and efficiency of knowledge structures allow uc to hold an interactive conversation with a user. 1. Introduction uc is a natural language program that converses in English with users in the domain of the UNIX operating system uc provides information on usage of system utilities UNIX terminology and plans for accomplishing specific tasks in the UNIX environment all upon direct query by the user. In order to accomplish these tasks uc must perforce have a considerable knowledge base a large part of which is particular to the UNIX domain. The specific representations used in this knowledge base are essential to the successful operation of uc. Not only are the knowledge structures used in parsing inference planning goal detection and generation but also the format of representation must permit the high efficiency in access and processing of the knowledge that is required in an interactive system like uc. This paper describes the details of this representation scheme and how it manages to satisfy these goals of usability and efficiency. Other aspects of the uc system are described in Arens 1982 Faletti 1982 Jacobs 1983 Rau 1983 and Wilensky and Arens 1980a and b . An overview of the uc system can be found in Wilensky 1982 . UNIX 18 tridemirk of Deli Liboritonea f Thia research WM sponsored