Knowledge Management for Biomedical Literature: The Function of Text-Mining Technologies in Life-Science Research

摘要

Efficient information retrieval and extraction is a major challenge in life-science research. The Knowledge Management (KM) for biomedical literature aims to establish an environment, utilizing information technologies, to facilitate better acquisition, generation, codification, and transfer of knowledge. Knowledge Discovery in Text (KDT) is one of the goals in KM, so as to find hidden information in the literature by exploring the internal structure of knowledge network created by the textual information. Knowledge discovery could be major help in the discovery of indirect relationships, which might imply new scientific discoveries. Text-mining provides methods and technologies to retrieve and extract information contained in free-text automatically. Moreover, it enables analysis of large collections of unstructured documents for the purposes of extracting interesting and non-trivial patterns of knowledge. Biomedical text-mining is organized in stages classified into the following steps: identification of biological entities, identification of biological relations and classification of entity relations. Here, we discuss the challenges and function of biomedical text-mining in the KM for biomedical literature.