Year: 2018
Type: conference-paper
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.
DOI: 10.18653/v1/w18-6202
Authors: Suzana Ilić, Edison Marrese-Taylor, Jorge Balazs, Yutaka Matsuo
Institutions: The University of Tokyo, Universität Innsbruck
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2964101952