Extracting knowledge from diagnostic databases

Author

Uthurusamy, Ramasamy ; Means, Linda G. ; Godden, Kurt S. ; Lytinen, Steven L.

Author_Institution

Gen. Motors Res. Labs., Warren, MI, USA

Volume

8

Issue

6

fYear

1993

Firstpage

27

Lastpage

38

Abstract

The use of natural language processing and machine learning techniques to help interpret, characterize, and standardize data, thereby enhancing the extraction of knowledge from diagnostic databases, is discussed. In particular Lexfix, a vocabulary correction and standardization system, has been designed to improve keyword-based retrieval on free-form text fields in GM´s Technical Assistance System (TAS) database, which contains about 300000 cases of vehicle symptoms and repair information. Also implemented was a natural language parser called TASLink, designed to interpret various kinds of ill-formed English, particularly free-form descriptions of vehicle faults. Inferule, an inductive machine-learning system that infers diagnostic rules from database cases containing information about vehicle symptoms and their solutions, is also described.<>

Keywords

automobile industry; diagnostic expert systems; natural language interfaces; query processing; GM´s Technical Assistance System; Inferule; Lexfix; TASLink; database; diagnostic databases; diagnostic rules; inductive machine-learning system; keyword-based retrieval; machine learning; natural language parser; natural language processing; repair information; vehicle symptoms; vocabulary correction; Collaboration; Data mining; Databases; Information retrieval; Laboratories; Monitoring; Natural language processing; Personnel; Standardization; Vehicles;

fLanguage

English

Journal_Title

IEEE Expert

Publisher

ieee

ISSN

0885-9000

Type

jour

DOI

10.1109/64.248350

Filename

248350