11 novembre 2016
https://creativecommons.org/licenses/by-nc-nd/4.0/ , info:eu-repo/semantics/openAccess
Lorenzo Gregori et al., « Linking dei contenuti multimediali tra ontologie multilingui: i verbi di azione tra IMAGACT e BabelNet », Accademia University Press, ID : 10.4000/books.aaccademia.1484
We present a study dealing with the linking between two multilingual and multimedial resources, BabelNet and IMAGACT. The task aims to connect the videos contained in the IMAGACT Ontology of Actions and the related verb entries in BabelNet. The linking experiment is based on an algorithm that exploits the lexical information of the two resources. The results show that is possible to achieve an extensive linking between the two ontologies. This linking is highly desirable in order to build a rich multimedial knowledge base that can be exploited for the following complex tasks: the reference disambiguation and the automatic/assisted translation of both the verbs and the sentences which refer to actions.