# Deep contextualized word representations for detecting sarcasm and irony

arXiv: https://arxiv.org/abs/1809.09795 · HTML: https://mlsanity.com/paper/1809.09795/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2018.

## Built on by (most cited first, 18 of 18)

- [On Sarcasm Detection with OpenAI GPT-based Models](https://mlsanity.com/paper/2312.04642/) (2023)
- [Sarcasm Detection: A Comparative Study](https://mlsanity.com/paper/2107.02276/) (2021)
- [A Survey in Automatic Irony Processing: Linguistic, Cognitive, and Multi-X Perspectives](https://mlsanity.com/paper/2209.04712/) (2022)
- [UTNLP at SemEval-2022 Task 6: A Comparative Analysis of Sarcasm Detection Using Generative-based and Mutation-based Data Augmentation](https://mlsanity.com/paper/2204.08198/) (2022)
- [ContrastNER: Contrastive-based Prompt Tuning for Few-shot NER](https://mlsanity.com/paper/2305.17951/) (2023)
- [Computational Sarcasm Analysis on Social Media: A Systematic Review](https://mlsanity.com/paper/2209.06170/) (2022)
- [Sarcasm Detection Framework Using Context, Emotion and Sentiment Features](https://mlsanity.com/paper/2211.13014/) (2022)
- [Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detection](https://mlsanity.com/paper/2412.12761/) (2024)
- [Parallel Deep Learning-Driven Sarcasm Detection from Pop Culture Text and English Humor Literature](https://mlsanity.com/paper/2106.05752/) (2021)
- ["When Words Fail, Emojis Prevail": Generating Sarcastic Utterances with Emoji Using Valence Reversal and Semantic Incongruity](https://mlsanity.com/paper/2305.04105/) (2023)
- [Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features](https://mlsanity.com/paper/2405.02569/) (2024)
- [A Transformer and Prototype-based Interpretable Model for Contextual Sarcasm Detection](https://mlsanity.com/paper/2503.11838/) (2025)
- [Interpretable Multi-Head Self-Attention model for Sarcasm Detection in social media](https://mlsanity.com/paper/2101.05875/) (2021)
- [Automatic Detection of Industry Sectors in Legal Articles Using Machine Learning Approaches](https://mlsanity.com/paper/2303.05387/) (2023)
- [Researchers eye-view of sarcasm detection in social media textual content](https://mlsanity.com/paper/2304.08582/) (2023)
- [UT5: Pretraining Non autoregressive T5 with unrolled denoising](https://mlsanity.com/paper/2311.08552/) (2023)
- [Assessing how hyperparameters impact Large Language Models' sarcasm detection performance](https://mlsanity.com/paper/2504.06166/) (2025)
- [Odin: Oriented Dual-module Integration for Text-rich Network Representation Learning](https://mlsanity.com/paper/2511.21416/) (2025)

## Abstract (arXiv)

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.