Deep contextualized word representations for detecting sarcasm and irony

TL;DR

This paper introduces a model using character-level ELMo embeddings to detect sarcasm and irony, achieving state-of-the-art results across multiple datasets by capturing complex linguistic and contextual cues.

Contribution

The paper presents a novel approach leveraging character-level ELMo embeddings for improved detection of sarcasm and irony in NLP tasks.

Findings

Achieved state-of-the-art performance on 6 out of 7 datasets.

Demonstrated effectiveness of character-level embeddings in capturing nuanced language cues.

Provided competitive results on remaining datasets.

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.