Tech Reports

Tech Report kmi-06-12 Abstract

Fusing automatically extracted annotations for the Semantic Web
Techreport ID: kmi-06-12
Date: 2006
Author(s): Andriy Nikolov

One of the necessary preconditions of the Semantic Web initiative is the availability of semantic data. The Web already contains large amounts of information intended for human users. This information is mainly stored as hypertext, which must be semantically annotated to make it accessible for software agents. The amount of information on the Web makes it impossible to solve the annotation task manually. Therefore the use of automatic information extraction algorithms is essential. These algorithms use various NLP and machine learning techniques to extract information from text. The information extracted from different sources must then be integrated in a knowledge base, so that it can be queried in a uniform way. This integration process is called knowledge fusion. However, performing knowledge fusion encounters a number of problems. The origins of these problems are the following: 1. Inaccuracy of existing information extraction algorithms leads to appearance of incorrect annotations. 2. Information contained on the web pages can be imprecise, incomplete or vague. 3. Multiple sources can contradict each other. Thus, in order to perform large-scale automatic annotation it is necessary to implement a knowledge fusion procedure, which is able to deal with these problems. Existing studies, which deal with the fusion issue, are either focused on solving separate subtasks of the problem or are only limited to a specific domain. The goal of this project is to make a contribution into the Semantic Web research by proposing a generic fusion framework based, which will make possible combining existing methods in order to perform knowledge fusion in a domain-independent way.