Recently, biomedical researchers have been facing the vast repository of research papers, e.g. MEDLINE. These researchers are eager to search biomedical correlations such as protein-protein or gene-disease associations. The use of natural language processing technology is expected to reduce their burden, and various attempts of information extraction using NLP has been being made. However, the framework of traditional information retrieval (IR) has difficulty with the accurate retrieval of such relational concepts. This is because relational concepts are essentially determined by semantic relations of words, and keyword-based IR techniques are insufficient to describe such relations precisely.Here, we propose an intelligent search engine for the accurate retrieval of relational concepts from MEDLINE, MEDIE, and a GUI-based efficient MEDLINE search tool, Info-PubMed.
View full abstract