ACL/HCSNet Advanced Program in
Natural Language Processing

University of Melbourne, 10-14 July 2006

Sophia Ananiadou: Terminology Management and Information Extraction for Biology

Abstract

Text mining for biology is one of the fast growing areas of research. This tutorial will provide a critical overview of state-of-the-art techniques applied to text mining in the bio-sciences aiming to clarify what can be expected of the field at present, and in the near future. The tutorial will focus on two areas: terminology management and information extraction. Terminology processing is particularly challenging in biology given the amount of neology. This tutorial will describe techniques for term extraction, named entity recognition, handling term variation, acronym recognition and term classification. The second part of this tutorial will introduce technologies and resources that have been developed for information extraction in Biology. These include linguistically annotated biomedical corpora, various NLP tools that are designed to analyse biomedical text, and several approaches to extracting useful information from biomedical documents such as protein-protein interactions and disease-gene associations. Demonstrations of practical systems for terminology processing and information extraction in the field will be provided.

Biographical Sketch

Sophia Ananiadou is Reader in Text Mining in the School of Informatics, University of Manchester. She is also deputy director of The National Centre for Text Mining (http://www.nactem.ac.uk) focusing initially on text mining for the Life Sciences. Her main interests are in bio-text mining, natural language processing, automatic terminology management, and linguistic knowledge acquisition from biomedical texts. Her research has been funded by the EC, UK research councils and industry. She has co-edited Text mining in Biology and Biomedicine (2006, Artech House) and authored over 100 technical papers. She has organised workshops in biomedical text mining (ACL, Coling) and has given tutorials on similar topics in conferences such as PSB, ISMB, EACL MIE. She has served as PC member in numerous conferences and workshops, reviewed for various journals such as Bioinformatics, BMC Bioinformatics and has given invited talks on her research in Universities, industry and research institutes world wide.


ACL/HCSNet Advanced Program in Natural Language Processing