Authors:
Massimiliano Gioseffi
and
Angela Locoro
Affiliation:
University of Genova, Italy
Keyword(s):
Domain-driven Word Sense Disambiguation, Domain Ontologies, Text Classification, Natural Language Processing, Machine Translation.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Artificial Intelligence
;
e-Business
;
Enterprise Engineering
;
Enterprise Information Systems
;
Enterprise Ontologies
;
Formal Methods
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Natural Language Processing
;
Ontologies
;
Pattern Recognition
;
Simulation and Modeling
;
Symbolic Systems
Abstract:
In this paper we present an approach for the translation and classification of short texts in one step. Our work lays in the tradition of Domain-Driven Word Sense Disambiguation, though a major emphasis is given to domain ontologies as the right tool for sense-tagging and topic detection of short texts which, by their nature, are known to be reluctant to statistical treatment. We claim that in a scenario where users can annotate knowledge items using different languages, domain ontologies can prove very suitable for driving the word disambiguation and topic classification tasks. In this way, two tasks are gainfully collapsed in a single one. Although this study is still in its infancy, in what follows we are able to articulate motivations, design, workflow analysis, and concrete evolutions envisioned for our tool.