UNIBA - Integrating distributional semantics features in a supervised approach for detecting irony in Italian tweets
Fiche du document
5 juin 2019
- doi: 10.4000/books.aaccademia.4620
- isbn: 9788831978422
- eisbn: 9788831978699
https://creativecommons.org/licenses/by-nc-nd/4.0/ , info:eu-repo/semantics/openAccess
Mots-clés
elaborazione del linguaggio naturale strumenti del linguaggio traitement du langage naturel outils du langage Natural Language Processing Speech Tools Language & Linguistics LAN009000 CFSujets proches
Language (New words, slang, etc.) Skills training SarcasmCiter ce document
Pierpaolo Basile et al., « UNIBA - Integrating distributional semantics features in a supervised approach for detecting irony in Italian tweets », Accademia University Press, ID : 10.4000/books.aaccademia.4620
Métriques
Partage / Export
Résumé
This paper describes the UNIBA team participation in the IronITA 2018 task at EVALITA 2018. We propose a supervised approach based on LIBLINEAR that relies on keyword, polarity, micro-blogging features and representation of tweets in a distributional semantic model. Our system ranked 3rd and 4th in the irony detection subtask. We participated only in the constraint run exploiting the training data provided by the task organizers.