Abstract: As the pace of biological research expedites, computers
have been used to manage the explosive amount of biological
information. Much of information relevant to biological research
is recorded either as coded data in genetic databases (e.g.,
GenBank) or as free text in journal articles and in annotation
fields of genetic databases. The excessive volume of information
propagating in free text has prompted researchers to explore
natural language processing (NLP) techniques to make the task of
managing all the relevant information more feasible. One
requirement for NLP in biology text is the ability to accurately
recognize biological entity name terms in free text. Other
requirements include an accurate part-of-speech tagging and a set
of relational pattern templates. In this talk, we will discuss an
ongoing project on developing a common NLP platform for NLP tools
in the biological domain which includes a biological entity
dictionary by mining genomic databases and
free text in the domain and a biological entity tagger which
takes ambiguity into consideration.