Information Extraction from Medical Literature
Meenakshi Narayanaswamy and K. E. Ravikumar
AU-KBC Research Centre
Chennai 600044 INDIA
Department of Computer and Information Sciences,
University of Delaware
Newark, DE 19716, USA
We have designed a new named entity extraction module as a part of information extraction system, which is based on a manually developed set of rules that rely heavily upon some crucial lexical information, linguistic constraints of English, and contextual information. This system achieves state of art results in the biological name detection task, which is what many of the current name extraction systems do. We detect chemical names and show that we not only obtain a high degree of success in recognizing chemicals but that this task can help improve the precision of protein name detection as well. We believe our use of context and sorrounding words for categorization of named entities is new and that the results obtained are encouraging. Currently we are developing system to automatically extract the interactions among the biological entities.
Meenakshi Narayanaswamy, Ravikumar.K.E., and K.Vijay-Shanker “A Biological Named Entity Recognizer “ accepted in Proceedings of the Pacific Symposium on Biocomputing '03 (PSB'03), Hawaii, January 2003.