In Biomedical research, retrieving documents that match an interesting query is a task performed quitefrequently. Typically, the set of obtained results is extensive containing many non-interesting documentsand consists in a flat list, i.e., not organized or indexed in any way. This work proposes BioDR, a novelapproach that allows the semantic indexing of the results of a query, by identifying relevant terms inthe documents. These terms emerge from a process of Named Entity Recognition that annotates occurrencesof biological terms (e.g. genes or proteins) in abstracts or full-texts. The system is based on a learningprocess that builds an Enhanced Instance Retrieval Network (EIRN) from a set of manually classifieddocuments, regarding their relevance to a given problem. The resulting EIRN implements the semanticindexing of documents and terms, allowing for enhanced navigation and visualization tools, as well asthe assessment of relevance for new documents.
展开▼