Information retrieval with commonsense knowledge

This paper employs ConceptNet, which covers a rich set of commonsense concepts, to retrieve images with text descriptions by focusing on spatial relationships. Evaluation on test data of the 2005 ImageCLEF shows that integrating commonsense knowledge in information retrieval is feasible. Categories and Subject Descriptors H.3.3 [Information Search and Retrieval]: Retrieval Models General terms Experimentation, Performance Keywords Commonsense Knowledge, ConceptNet, Concept Expansion

• Type: Conference
• Year: 2006
• Where: SIGIR
• Authors: Ming-Hung Hsu, Hsin-Hsi Chen
• Keywords: Commonsense Concepts, Commonsense Knowledge, Keywords Commonsense Knowledge, SIGIR 2006