Several NLP studies address the problem of figurative language, but among non-literal phenomena, they have neglected exaggeration. This paper presents a first computational approach to this figure of speech. We explore the possibility to automatically detect exaggerated sentences. First, we introduce HYPO, a corpus containing overstatements (or hyperboles) collected on the web and validated via crowdsourcing. Then, we evaluate a number of models trained on HYPO, and bring evidence that the task of hyperbole identification can be successfully performed based on a small set of semantic features.

A Computational Exploration of Exaggeration / Troiano, Enrica; Strapparava, Carlo; Gözde, Özbal; Tekiroglu, Serra Sinem. - ELETTRONICO. - (2018), pp. 3296-3304. ((Intervento presentato al convegno 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP-2018) tenutosi a Brussels, Belgium nel October 31 - November 4, 2018.

A Computational Exploration of Exaggeration

Carlo Strapparava;Gözde Özbal;Serra Tekiroglu
2018

Abstract

Several NLP studies address the problem of figurative language, but among non-literal phenomena, they have neglected exaggeration. This paper presents a first computational approach to this figure of speech. We explore the possibility to automatically detect exaggerated sentences. First, we introduce HYPO, a corpus containing overstatements (or hyperboles) collected on the web and validated via crowdsourcing. Then, we evaluate a number of models trained on HYPO, and bring evidence that the task of hyperbole identification can be successfully performed based on a small set of semantic features.
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP-2018)
USA
Association for Computational Linguistics
978-1-948087-84-1
Troiano, Enrica; Strapparava, Carlo; Gözde, Özbal; Tekiroglu, Serra Sinem
A Computational Exploration of Exaggeration / Troiano, Enrica; Strapparava, Carlo; Gözde, Özbal; Tekiroglu, Serra Sinem. - ELETTRONICO. - (2018), pp. 3296-3304. ((Intervento presentato al convegno 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP-2018) tenutosi a Brussels, Belgium nel October 31 - November 4, 2018.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/343007
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? ND
social impact