Multilingual semantic elaboration in the DOSE platform
Proceedings of the 2004 ACM symposium on Applied computing
Automatic learning of text-to-concept mappings exploiting WordNet-like lexical networks
Proceedings of the 2005 ACM symposium on Applied computing
Applying RST relations to semantic search
TSD'06 Proceedings of the 9th international conference on Text, Speech and Dialogue
| Hi-index | 0.00 |
The paper proposes a Distributed Open Semantic Elaboration platform based on a modular multilingual enabled architecture, which includes ontology, annotations, lexical entities and search functions. The platform is implemented as a distributed set of services including: semantic annotations for document substructures (e.g. chapters, sections, paragraphs), an external annotation repository (based on XPath and XPointer technologies) that is automatically populated starting from a known ontology and a lexical representation of concept classes, and a semantic search engine used to extract and recombine relevant document fragments. Annotated resources may be XML or XHTML static or dynamic documents, and need not be stored nor modified. Preliminary experimental results are presented to show the feasibility and the advantages of the proposed approach.