The semantic annotation service provides a simple REST API designed for creating, updating and retrieving semantic annotations. The service orchestrates other components (existing annotation tools) in order to control and fully perform data analysis process, creates semantic form of the generated data and persists semantic data using semantic store. Annotations created by the service are modelled using the Modular Unified Tagging Ontology (MUTO) which is designed specifically for tagging and folksonomies. MUTO allows representing public and private tagging, simple and auto generated tags and others. It is also easily extensible since all concepts defined in MUTO ontology inherits from other more general ontologies like SKOS, SIOC or vocabularies as RDFS.
SERVICE DESCRIPTION
The semantic enrichment, also known as semantic annotation (or tagging), enhances the source data with a context that is linked to some structured knowledge of a domain or application (ontology), which can be then exploited by different applications and services. This is done by attaching additional information to various concepts (e.g., people, things, places, organizations, etc.) in a given text or any other content .
Since the newly discovered knowledge is described by standard ontologies, stored in machine-readable format and accessible through standard APIs and protocols, it can also be used for further machine processing allowing better integration with existing knowledge bases and their publication in the Linked Open Data (LOD) Cloud, discovering and understanding relations and dependencies between resources, as well as the implementation of all other kinds of user scenarios.
The current implementation of the semantic annotation service uses AgroTagger and Babelfly, and it represents annotations using the Modular Unified Tagging Ontology (MUTO) as underlying model. Babelfy is provides a unified, multilingual, graph-based approach to Entity Linking and Word Sense Disambiguation based on a loose identification of candidate meanings coupled with a densest subgraph heuristic which selects high-coherence semantic interpretations.
Babelfy is based on the BabelNet multilingual semantic network and jointly performs disambiguation and entity linking. Babelnet covers 284 languages and is obtained from the automatic integration of several sources including Wordnet, Wikipedia, Geonames, etc. AgroTagger applies text-mining on top of agri-food research outcomes. It is a keyword extractor that uses a subset of the AGROVOC thesaurus (about 2,5K concepts out of the total >40K concepts of AGROVOC) as a set of allowable keywords, used for indexing information resources.
SPECIAL ACCESS CONDITIONS
No
PREREQUISITES
No
CASE EXAMPLES
Metadata enrichment Indexing of resources Semantic search and tag-cloud based search.
SUCCESS STORY
SERVICE CAN BE COMBINED WITH
Marketplaces, repositories.
