R3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge

By Tuhin Chakrabarty, Debanjan Ghosh, Smaranda Muresan, Nanyun Peng. 2020

70 citations recorded by the source corpus.

We propose an unsupervised approach for sarcasm generation based on a non-sarcastic input sentence. Our method employs a retrieve-and-edit framework to instantiate two major characteristics of sarcasm: reversal of valence and semantic incongruity with the context, which could include shared commonsense or world knowledge between the speaker and the listener. While prior works on sarcasm generation predominantly focus on context incongruity, we show that combining valence reversal and semantic incongruity based on the commonsense knowledge generates sarcasm of higher quality. Human evaluation shows that our system generates sarcasm better than humans 34% of the time, and better than a reinforced hybrid baseline 90% of the time.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Symbolic Knowledge Distillation: from General Language Models to Commonsense Models (2021, background): “…learning through a conversational interface (Arabshahi et al., 2021), persona-and affect-aware conversation models (Kearns et al., 2020), ﬁgura-tive language understanding (Chakrabarty et al., 2020, 2021), story telling (Ammanabrolu et al., 2021a) and fantasy games (Ammanabrolu et al., 2021b).”
Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources (2021, background): “COMeT has been shown to generate unseen commonsense knowledge in ConceptNet with high quality, and much recent work has used it to provide commonsense background knowledge (Shwartz et al., 2020; Chakrabarty et al., 2020).”
The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation (2021, background): “Each paper was published between 2018 and 2020 at ACL, NAACL, or EMNLP, and we exclude papers that use AMT to evaluate more wellestablished generation tasks like machine translation, or summarization.3 Unlike previous surveys of evaluating generated text (Çelikyilmaz et al., 2020; van der Lee et al.”
Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations (2021, background): “Several tasks such as dialog generation (Majumder et al., 2020), creative text generation (Chakrabarty et al., 2020; Mao et al., 2019), and counterfactual generation (Bhagavat-ula et al., 2020) used commonsense for grounding.”
COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs (2020, background): “This flexibility allows them to be used out-of-the-box, and they have been applied to new, previously unexplored tasks, such as sarcastic comment generation (Chakrabarty et al. 2020), therapy chatbots (Kearns et al. 2020), and automated story plot generation (Ammanabrolu et al. 2020).”
AmbiPun: Generating Humorous Puns with Ambiguous Context (2022, background): “In addition to pun, there are many attempts to generate ﬁgurative language such as metaphor, simile (Chakrabarty et al., 2020b), sarcasm, etc. Yu and Wan (2019)”
Rationale-Inspired Natural Language Explanations with Commonsense (2021, unknown): “, 2020), creative text generation (Chakrabarty et al., 2020),”