Details of Group leader - Dr Sophia Ananiadou
 |
Post: Reader, Text Mining Phone: (0)161 306 3092 Email: Sophia.Ananiadou@manchester.ac.uk Website: Click Me |
Research Text Mining in the area of life sciences. |
Current Research
National Centre for Text Mining (NaCTeM)
NaCTeM is the first publicly funded text mining centre in the world. The aims of the centre are to provide services to the UK academic community in the areas of information retrieval, terminology management, information extraction, initially in life sciences. We have developed a set of tools such TerMine (see figure), an automatic terminology system, Info-PubMed, a protein-protein interaction system and Medie, an intelligent information extraction engine. For further details, please click here.
Bootstrapping of Bio-Ontologies and Bio-Terminologies (BOOTStrep)
The aim of this project, funded under the 6th EC Framework Programme, is to build two major reusable, wide-coverage lexical and conceptual repositories for the biology domain, i.e. a bio-lexicon and a bio-ontology using text mining techniques and to harmonise and augment existing bio-terminologies and bio-ontologies. For further details please click here.
Automatic Summarisation
This JISC funded project, is directly linked with NaCTeM. It centres around providing broader institutional involvement in text mining through a community call, while at the same time developing an exemplar summarisation service for the social sciences domain. As a whole, this project strongly contributes to the outcomes required by the e-Infrastructure programme, that is greater participation by the social sciences in e-Research and greater usage of the Grid for social science and arts and humanities based e-Research. The overall aim is to facilitate the production of systematic reviews in cooperation with the EPPI.
• Interoperability of Text Mining tools.
This project is funded by IBM and enhances the current work performed by NaCTeM in collecting and developing software modules of text mining and distributing them in interoperable form. Enabler layers add all the benefits of typed feature structure-based logic programming (LiLFeS) to a collection of software in UIMA compliant forms. NaCTeM will distribute the end results of the UIMA compliant unification engine and LiLFeS to the user community of natural language processing and text mining.
Service & Awards
- Deputy Director of the National Centre for Text Mining (2004-)
- UIMA Innovation Award (2006)
- Daiwa Adrian award (UK Team leader, 2004)
Funding
BBSRC - EPSRC - EU - IBM - JISC
Recent Publications
- Ananiadou, S., Kell, D.B. and Tsujii, J., Text Mining and its Potential Applications in Systems Biology, Trends in Biotechnology (TIBTECH), , (accepted), 2006.
- Ananiadou, S. & McNaught, J. (eds.), Text Mining for Biology and Biomedicine, Artech House, ISBN 1-58053-984-X, , , , 2006.
- Okazaki, N. & Ananiadou, S., A Term Recognition Approach to Acronym Recognition, Proc. Coling / ACL, , 643-650, 2006.
- Mima, H., Ananiadou, S. & Katsushima, M., Terminology-based Knowledge Mining for New Knowledge Discovery, ACM Transactions on Asian language information processing, 5, 74-88, 2006.
- Nenadic G. and Ananiadou, S., Mining Semantically Related Terms from Biomedical Literature, ACM Transactions on Asian Language Information Processing, 5, 1-22, 2006.
- Tsujii, J. & Ananiadou, S., Thesaurus or logical ontology, which one do we need for text mining?, Language Resources and Evaluation, Springer Science and Business Media B.V., 39, 77-90, 2005.
- Spasic, I., Ananiadou, S. and Tsujii, J., MaSTerClass: a case-based reasoning system for the classification of biomedical terms, Bioinformatics, 21, 2748-2758, 2005.