Nice perfume. How long did you marinate in it? Multimodal Sarcasm Explanation
This addresses the challenge of making sarcasm understandable for end users in social media and online platforms, though it is incremental as it builds on existing multimodal and Transformer-based methods.
The paper tackles the problem of explaining sarcasm in multimodal posts by introducing the Multimodal Sarcasm Explanation (MuSE) task, where they generate natural language explanations for sarcastic content, achieving convincing results across five evaluation metrics and a human evaluation Fleiss' Kappa score of 0.4.
Sarcasm is a pervading linguistic phenomenon and highly challenging to explain due to its subjectivity, lack of context and deeply-felt opinion. In the multimodal setup, sarcasm is conveyed through the incongruity between the text and visual entities. Although recent approaches deal with sarcasm as a classification problem, it is unclear why an online post is identified as sarcastic. Without proper explanation, end users may not be able to perceive the underlying sense of irony. In this paper, we propose a novel problem -- Multimodal Sarcasm Explanation (MuSE) -- given a multimodal sarcastic post containing an image and a caption, we aim to generate a natural language explanation to reveal the intended sarcasm. To this end, we develop MORE, a new dataset with explanation of 3510 sarcastic multimodal posts. Each explanation is a natural language (English) sentence describing the hidden irony. We benchmark MORE by employing a multimodal Transformer-based architecture. It incorporates a cross-modal attention in the Transformer's encoder which attends to the distinguishing features between the two modalities. Subsequently, a BART-based auto-regressive decoder is used as the generator. Empirical results demonstrate convincing results over various baselines (adopted for MuSE) across five evaluation metrics. We also conduct human evaluation on predictions and obtain Fleiss' Kappa score of 0.4 as a fair agreement among 25 evaluators.