Extracting knowledge from diagnostic databases

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.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>