Enriching Ontologies with Encyclopedic Background Knowledge for Document Indexing
This addresses the problem of efficient document management for researchers and information systems, but appears incremental as it builds on existing ontology-based and machine learning methods.
The paper tackles the challenge of automatically organizing and indexing scientific documents by proposing an approach that enriches domain-specific ontologies with encyclopedic background knowledge to improve classification and indexing methods.
The rapidly increasing number of scientific documents available publicly on the Internet creates the challenge of efficiently organizing and indexing these documents. Due to the time consuming and tedious nature of manual classification and indexing, there is a need for better methods to automate this process. This thesis proposes an approach which leverages encyclopedic background knowledge for enriching domain-specific ontologies with textual and structural information about the semantic vicinity of the ontologies' concepts. The proposed approach aims to exploit this information for improving both ontology-based methods for classifying and indexing documents and methods based on supervised machine learning.