Maintaining updated ontology-based digital libraries faces two main issues. First, documents are often unstructured and in heterogeneous data formats, making it even more difficult to extract information and search in. Second, manual ontology population is time consuming and therefore automatic methods to support this process are needed. In this paper, we present an ontology-based framework aiming at populating ontologies. In particular, we propose an approach for triplet extraction from heterogeneous and unstructured documents in order to automatically populate ontology-based digital libraries. Finally, we evaluate the proposed framework on a real world case study.
A framework for automatic population of ontology-based digital libraries / Pandolfo, Laura; Pulina, Luca; Adorni, Giovanni. - 10037:(2016), pp. 406-417. (Intervento presentato al convegno 15th International Conference on Italian Association for Artificial Intelligence, AIIA 2016 tenutosi a ita nel 2016) [10.1007/978-3-319-49130-1_30].
A framework for automatic population of ontology-based digital libraries
PANDOLFO, LAURA;PULINA, Luca;
2016-01-01
Abstract
Maintaining updated ontology-based digital libraries faces two main issues. First, documents are often unstructured and in heterogeneous data formats, making it even more difficult to extract information and search in. Second, manual ontology population is time consuming and therefore automatic methods to support this process are needed. In this paper, we present an ontology-based framework aiming at populating ontologies. In particular, we propose an approach for triplet extraction from heterogeneous and unstructured documents in order to automatically populate ontology-based digital libraries. Finally, we evaluate the proposed framework on a real world case study.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
