Biological information embedded within the large repository of unstructured or semi-structured text documents can be extracted
more efficiently through effective semantic analysis of the texts in collaboration with structured domain knowledge. The GENIA
corpus houses tagged MEDLINE abstracts, manually annotated according to the GENIA ontology, for this purpose. However, manual
tagging of all texts is impossible and special purpose storage and retrieval mechanisms are required to reduce information
overload for users. In this paper we have proposed an ontology-based biological Information Extraction and Query Answering
(BIEQA) system that has four components: an ontology-based tag analyzer for analyzing tagged texts to extract Biological and
lexical patterns, an ontology-based tagger for tagging new texts, a knowledge base enhancer which enhances the ontology, and
incorporates new knowledge in the form of biological entities and relationships into the knowledge base, and a query processor
for handling user queries.
Keywords Ontology-based text mining - Biological information extraction - Automatic tagging