Research – Paper 225
Andon Tchechmedjiev, Théophile Mandon, Mathieu Lafourcade, Anne Laurent and Konstantin TodorovResearch
October 23, 2017, 14:00.
Download paper (preprint)
JeuxDeMots (JdM) is a rich collaborative lexical network in French, built on a crowdsourcing principle as a game with a purpose, represented in an ad-hoc tabular format. In the interest of reuse and interoperability, we propose a conversion algorithm for JdM following the Ontolex model, along with a word sense alignment algorithm, called JdMBabelizer, that anchors JdM sense-refinements to synsets in the lemon edition of BabelNet and thus to the Linguistic Linked Open Data cloud. Our alignment algorithm exploits the richness of JdM in terms of weighted semantic-lexical relations—particularly the inhibition relation between senses—that are specific to JdM. We produce a reference alignment dataset for JdM and BabelNet that we use to evaluate the quality of our algorithm and that we make available to the community. The obtained results are comparable to those of state of the art approaches.