Deep contextualized word representations for detecting sarcasm and irony

Suzana Ilić, Edison Marrese-Taylor, Jorge Balazs, Yutaka Matsuo


Abstract
Predicting context-dependent and non-literal utterances like sarcastic and ironic expressions still remains a challenging task in NLP, as it goes beyond linguistic patterns, encompassing common sense and shared knowledge as crucial components. To capture complex morpho-syntactic features that can usually serve as indicators for irony or sarcasm across dynamic contexts, we propose a model that uses character-level vector representations of words, based on ELMo. We test our model on 7 different datasets derived from 3 different data sources, providing state-of-the-art performance in 6 of them, and otherwise offering competitive results.
Anthology ID:
W18-6202
Volume:
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Alexandra Balahur, Saif M. Mohammad, Veronique Hoste, Roman Klinger
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2–7
Language:
URL:
https://aclanthology.org/W18-6202
DOI:
10.18653/v1/W18-6202
Bibkey:
Cite (ACL):
Suzana Ilić, Edison Marrese-Taylor, Jorge Balazs, and Yutaka Matsuo. 2018. Deep contextualized word representations for detecting sarcasm and irony. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 2–7, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Deep contextualized word representations for detecting sarcasm and irony (Ilić et al., WASSA 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6202.pdf
Code
 epochx/elmo4irony
Data
SARC