Attentional Multi-Reading Sarcasm Detection

TL;DR

This paper introduces an interpretable end-to-end model that effectively combines utterance and conversational context to improve sarcasm detection, providing explanations and analyzing component contributions.

Contribution

The paper presents a novel model that integrates multiple information sources for sarcasm detection and offers interpretability and analysis of decision factors.

Findings

The model outperforms existing systems in sarcasm detection accuracy.

It provides explanations for its decisions based on context and utterance.

Ablation studies show the importance of different model components.

Abstract

Recognizing sarcasm often requires a deep understanding of multiple sources of information, including the utterance, the conversational context, and real world facts. Most of the current sarcasm detection systems consider only the utterance in isolation. There are some limited attempts toward taking into account the conversational context. In this paper, we propose an interpretable end-to-end model that combines information from both the utterance and the conversational context to detect sarcasm, and demonstrate its effectiveness through empirical evaluations. We also study the behavior of the proposed model to provide explanations for the model's decisions. Importantly, our model is capable of determining the impact of utterance and conversational context on the model's decisions. Finally, we provide an ablation study to illustrate the impact of different components of the proposed model.