Authors:
Ibrahim Soumana
;
Sylviane Cardey
and
Peter Greenfield
Affiliation:
Université de Franche Comté, France
Keyword(s):
Natural Language Interface for Database, NLIDB, NLI, Lexicon, Interclass Lexicon, Intraclass Lexicon, RDF Triple, Ontology, Operator, Function, Natural Language Processing.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Artificial Intelligence
;
Collaboration and e-Services
;
e-Business
;
Enterprise Information Systems
;
Human-Machine Cooperation
;
Knowledge Engineering and Ontology Development
;
Knowledge Representation
;
Knowledge-Based Systems
;
Natural Language Processing
;
Ontology Sharing and Reuse
;
Pattern Recognition
;
Semantic Web
;
Soft Computing
;
Symbolic Systems
Abstract:
Data volume growth leads to new challenges for Natural Language Interfaces (NLI). With Big Data for example, NLI must not only be portable from one domain to another, but be operational simultaneously in several domains. The lexicon is an important resource that improves the system performance. In this paper, we propose an approach to design a lexicon centered on RDF (Resource Description Framework) triple. We argue that a triple centric lexicon is reusable. The lexicon is also extended to include operations and possible functions in which data can be involved. This allows increasing the complexity of questions a NLI can process.