Named Entity Recognition Ontology

Other names: NERO

Named Entity Recognition Ontology (NERO) developed specifically for describing textual entities in biomedical texts, which accounts for diverse levels of ambiguity, bridging the scientific sublanguages of molecular biology, genetics, biochemistry, and medicine. The annotation of natural science texts is more challenging than in other domains. Biomedical language is replete with ambiguity distinct from that observed in news articles or informal text online. In biomedical texts, alternative meanings are not always clearly separated. For example, in some biomedical contexts, the words for a named entity may refer to a gene or a protein with nearly equal probability; for example, “a mutant hemoglobin α_2” can refer to either a gene or a protein. If the author meant gene-or-protein A, and we force an annotator to choose either interpretation gene A or protein A, the resulting annotation is of limited utility because the choice between gene and protein is random if the meanings are equally likely based on context. NERO attempts to minimize unwarranted, arbitrary annotative semantic label assignments for textual entities. NERO defines ambiguous concepts, such as GeneOrProtein, which subsumes both Gene and Protein using the following axiom: EquivalentTo: ‘Gene’ or ‘Protein.’ There are no biological entities that are either a gene or a protein, but there are lexical entities that can correspond to either or both of these entities.

More to explore:

1/20

Previous Next   



Need help integrating and/or managing biomedical data?