About Semantic Technology Group


Leveraging knowledge sources external to a corporation costs information professionals approximately 20% of their time searching and analyzing the literature. Recent reports have identified that digital information available as semi-structured (e.g. XML) and unstructured data is estimated to comprise of 53% of all available information in enterprises, and little unstructured (natural language text) or semi-structured data makes its way into data warehouses. Furthermore, state-of-the-art search technologies for accessing information from online sources produce highly efficient query issue but are in-effective in delivering targeted results.

Recent advances in the domain of semantic web and data integration technology make it possible to index diverse data types and formats according to domain specific semantic metadata, which can be used as a query model for searching. While these approaches have been proven in prototype scale, commercial deployments of such technology are relatively few. This is, in part, because the full skill set required to build semantically enhanced knowledge-bases and domain-specific vertical search tools is necessarily broad. It requires teams of researchers and developers skilled in, knowledge capture and ontology engineering, text mining and natural language processing, ontology based reasoning and interface design. Building and maintaining such teams represents a competitive edge for rapid redeployment of this hybrid technology and for market entry.

The Semantic Technology Group has worked in this problem space for 3 years already and has been early adopters of semantic technology. We focus on developing service-oriented knowledge navigation and discovery infrastructures using text mining, ontologies, and reasoning techniques, that enable visual query navigation and data mining of unstructured, semi-structured and structured data indexed with OWL-DL ontologies.


Our group has developed a service-oriented semantic technology platform, called the Knowle that has been successfully applied to develop semantic applications for campaign management, biomedical, patent analysis and business intelligence domains. The Knowle platform can be rapidly customized to create new applications for knowledge aggregation, integration, search and mining across heterogeneous data sources (structured databases,web,text), with minimal man month effort. Go here to view demos.



Publications - Semantic Technology Group


  • Menaka Rajapakse,Rajaraman Kanagasabai,Ang Wee Tiong,Anita Veeramani and Christopher Baker. Ontology-centric knowledge integration and navigation of the dengue literature. Journal of Biomedical Informatics. Special Issue on Semantic BioMed Mashup, 2008. Link.

  • Christopher Baker, Rajaraman Kanagasabai, Ang Wee Tiong, Anitha Veeramani, Hong-Sang Low, Markus R. Wenk. Towards ontology-driven navigation of the lipid bibliosphere. BMC Bioinformatics 9 Suppl 1 , S5 (2008). Link.

  • Edward Wijaya, Siu Ming, Song NT, Rajaraman Kanagasabai, Ken Sung. MotifVoter: a novel ensemble method for fine-grained integration of generic motif finders. Bioinformatics, Aug 2008. Link.

  • Rajaraman Kanagasabai, Choo Khar Heng and Christopher Baker. A Workflow for Mutation Extraction and Structure Annotation. Jl. of Bioinformatics and Computational Biology. Special Issue: Making Sense of Mutations Requires Knowledge Management. . Vol 5 No 6. Dec 2007. Link


  • Wee Tiong Ang, Wei-Peng Seeto, Francis Tan, Weng-Fai Tang, Rajaraman Kanagasabai. Ontology-centric, Service-Oriented Enterprise Campaign Management System. IEEE International Conference on Semantic Computing 2009, Berkeley, USA. (Accepted.)

  • Christopher Baker, Patrick Lambrix, Jonas Laurila Bergman, Rajaraman Kanagasabai and Wee Tiong Ang. Slicing through the scientific literature. Data integration in Life sciences Workshop 2009, UK. (To appear) Link.

  • Keng Yew, Ang Wee Tiong, Flora Tsai, Rajaraman Kanagasabai. OntoMobiLe: A Generic Ontology-centric
    Service-Oriented Architecture for Mobile Learning . Mobile Data Management Workshop on 'Mobile Multimedia Retrieval', Taiwan, 2009. (Accepted.)

  • Rajaraman Kanagasabai, Kothandaraman Narasimhan, Hong-Sang Low, Wee Tiong Ang, Aaron Z. Fernandis, Markus R. Wenk, Mahesh A. Choolani, and Christopher J. O. Baker. Mining to Find the Lipid Interaction Networks Involved in Ovarian Cancers. Proc. of AMIA Summit on Translational Bioinformatics, San Francisco, USA, Mar 2009. (To appear.)

  • Wee Tiong Ang, Rajaraman Kanagasabai and Christopher Baker. Knowledge Translation: Computing the query potential of bio-ontologies. Proc. of Semantic Web Applications and Tools for Life Sciences Workshop, UK, Dec 2008. Link.

  • Rajaraman Kanagasabai, Hong-Sang Low, Ang Wee Tiong, Markus R. Wenk, Christopher Baker. Ontology-centric navigation of pathway information mined from text. Bio-Ontologies 2008: Knowledge in Biology, ISMB 2008. Link.

  • Rajaraman Kanagasabai and Christopher Baker. Extraction and Grounding of Protein Mutations via Ontology-centric Knowledge Integration. Proc of RECOMB 2008, Singapore.

  • Rajaraman Kanagasabai, Hong-Sang Low, Ang Wee Tiong, Anitha Veeramani, Markus R. Wenk, Christopher Baker. Literature-driven Ontology-centric knowledge navigation in Lipidomics. Proceedings of the Workshop on the First Industrial Results of Semantic Technologies (FIRST2007) at 6th International Semantic Web Conference, Busan, South Korea, 2007. . Link


  • SG110980, Method and System for Discovering Knowledge from Text Documents, Tan Ah Hwee, Kanagasabai Rajaraman. Granted Date: 30 Apr 07.