188/4 E-Commerce Group
Institute of Software Technology and Interactive Systems
Vienna University of Technology
Favoritenstrasse 9-11/188, A-1040 Vienna, Austria

Wissensextraktion aus Dokumenten

Type: 
Master Thesis
State: 
completed
First name: 
Clemens
Last name: 
Kahlig
Matr nr: 
9426584
Language: 
Deutsch
Supervisor: 
Dorn, J.
Abstract: 
This work describes the process of automation of documents. A data-extractor is developed to gain the main information of a document, which is classified into different categories. The content of the document is analysed. Error Detection of different error classes is made by a method of error correction, which is developed and realized. For example, bills are taken into account to show the processing in use. The documents are scanned and transformed into data by using a method of data-extraction developed and described in this work. Cases of influences of the processing are discussed and shown by examples. Bills, used for demonstration, can easily be replaced by other equivalent, text-oriented documents. The methods are constructed for documents of any type containing data to extract. Finally, ways are presented to make the methods of data-extraction more reliable.
Issued: 
Nov 2000
Started: 
2000-11-01
Finished: 
2002-11-01