Word Sense Disambiguation and Lexical Substitution (WSD&LS)

(This task has been cancelled)

We propose a Word Sense Disambiguation (WSD) task. WSD is the task of automatically associating meaning with words in context. Meanings are selected from an existing sense inventory (e.g., from WordNet).
(The initially proposed Lexical Substitution task, associated with the WDS task, has been cancelled. We apologize for this.)

We use BabelNet 2.0 as our sense inventory, thanks to its coverage of Italian, among its 50 languages. BabelNet is a very large multilingual encyclopedic dictionary and semantic network.

As regards WSD, given an input sentence and a target word, the systems are required to disambiguate the target word with a correct sense from BabelNet.

Detailed guidelines, task materials and data sets for development, training and testing will be made available on the Task Website.


  • Daniele Vannella (Sapienza Università di Roma)
    Roberto Navigli (Sapienza Università di Roma)


Daniele Vannella vannella[at]di.uniroma1.it