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.
@article{arxiv.1809.09795,
title = {Deep contextualized word representations for detecting sarcasm and irony},
author = {Suzana Ilić and Edison Marrese-Taylor and Jorge A. Balazs and Yutaka Matsuo},
journal= {arXiv preprint arXiv:1809.09795},
year = {2018}
}