Institute of Information Science Academia Sinica
Topic: Toward Semantic Web for Biomedical Literature: Information extraction and ontology alignment
Speaker: Prof. Jung-jae Kim (Nanyang Technological University, Singapore )
Date: 2012-10-03 (Wed) 10:30 – 12:00
Location: Auditorium 106 at new IIS Building
Host: Wen-Lian Hsu

Abstract:

Semantic Web technologies have great potential for improving search results, especially in the biomedical domain where biologists have been intensively developing community-curated ontologies. We can apply the technologies to biomedical literature to represent the information expressed in biomedical documents with the concepts and relations of the biomedical ontologies. When successfully represented, the information stored into the ontologies will allow us to perform fine-tuned semantic searches over the literature.

In this talk, we show a feasibility test toward the goal in two aspects: 1) an ontology-based text mining system that extracts the information expressed in biomedical documents by using logical inference based on domain knowledge and 2) ontology alignment methods for equivalence and subsumption relation identification for automatic ontological corpus annotation and cross-ontology semantic querying. The first system identifies textual semantics and represents them with an ontology called GRO. One of its advanced features is to deduce implicit information from explicitly expressed information by using inference rules that encode domain knowledge. The resultant GRO-based semantics, both explicit and implicit, are stored into the ontology and can be retrieved by a semantic search engine. The second part assumes that we can extract such textual semantics based on multiple ontologies individually, and enables to query across the integrated ontologies that are populated with the textual semantics. It requires the integration of the ontologies through cross-ontology correspondences like equivalence and subsumption relations. We introduce novel methods for the tasks.        

Jung-jae Kim is currently an Assistant Professor of the School of Computer Engineering at Nanyang Technological University (NTU) in Singapore. He received his BSc, MS, and PhD in 1998, 2000, and 2006, respectively, from KAIST, South Korea. He has worked as a post-doctoral researcher for the European Bioinformatics Institute (EBI) from 2006 to 2009. I am an editor of the Journal of Biomedical Semantics and served as Publicity Chair of ACL 2012, Program Chair of LBM 2011, and PC members of such conferences as ISMB, ECCB, IHI, and LREC.