GRO Task: Populating the Gene Regulation Ontology with events and relations
نویسندگان
چکیده
Semantic querying over the biomedical literature has gained popularity, where a semantic representation of biomedical documents is required. Previous BioNLP Shared Tasks exercised semantic event extraction with a small number of pre-defined event concepts. The GRO task of the BioNLP’13-ST imposes the challenge of dealing with over 100 GRO concepts. Its annotated corpus consists of 300 MEDLINE abstracts, and an analysis of interannotator agreement on the annotations by two experts shows Kappa values between 43% and 56%. The results from the only participant are promising with F-scores 22% (events) and 63% (relations), and also lead us to open issues such as the need to consider the ontology structure.
منابع مشابه
Discovering Cross-Ontology Subsumption Relationships by Using Ontological Annotations on Biomedical Literature
Cross-ontology concept subsumption relationships facilitate the integration of ontologies by explicitly defining the generalization of a concept over other concepts in different ontologies. However, existing methods for discovering these relationships show poor performances and one of the problems is the lack of instance data in ontologies that can be used to identify cross-ontology subsumption...
متن کاملSemantic representation of Gene Ontology terms by using Gene Regulation Ontology
Gene Ontology (GO) has been developed to provide concepts for the functional annotation of biological entities. This development has already contributed to significant biomedical research results. Nonetheless, GO could have provided even stronger support to biomedical text mining, if it delivered domain-independent logical definitions of its concepts. We present a method that extracts the seman...
متن کاملOntology-based Technical Text Annotation
Powerful tools could help users explore and maintain domain specific documentations, provided that documents have been semantically annotated. For that, the annotations must be sufficiently specialized and rich, relying on some explicit semantic model, usually an ontology, that represents the semantics of the target domain. In this paper, we learn to annotate biomedical scientific publications ...
متن کاملOntology-based Extraction of Transcription Regulation Events
I present an on-going work on extraction of transcription regulation events from text by using an ontology which plays a central role in integrating information from different sources. The events of transcription regulation are expressed in the literature with a high degree of compositeness. They have elements such as event types, participants, and attributes. These elements are associated with...
متن کاملOn the expressive limits of reified theories
Reified theories have been used widely in knowledge representation. From an ontological perspective, reification involve populating the ontology with event or property types and tokens. While type reification has been used in many works, it has been criticized as being philosophically unsound, and token reification has been advocated in its place by Galton. In this paper, we take the position o...
متن کامل