Elamur Research⌕
☰
home / papers / 2020 / R^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge

R^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge

Summary

The paper addresses sarcasm generation, a task with almost no training data. It turns a literal, negatively evaluative sentence into a sarcastic one without supervision. The authors build a retrieve-and-edit pipeline, R^3, around two sarcasm factors from linguistic theory:

  1. Reversal of valence. The evaluative word is replaced with its WordNet antonym, or a negation is added or removed.
  2. Commonsense retrieval. COMET, a language model fine-tuned on ConceptNet, infers a commonsense consequence of the input (fast food leads to stomach ache). This consequence is used to retrieve candidate context sentences from a corpus.
  3. Incongruity ranking. A RoBERTa model trained on the Multi-Genre NLI Corpus scores how strongly each candidate contradicts the flipped sentence. The most contradictory candidate is appended.

The system was tested on 150 literal sentences sampled from two existing datasets. MTurk workers judged sarcasticness, humor, creativity and grammaticality. R^3 beat a reinforced hybrid baseline (Mishra et al., 2019) in 90% of comparisons and was preferred over human-written sarcasm in 34%. The work shows that explicitly modeling commonsense-based incongruity improves creative text generation.

Key points

  • The three modules are valence reversal (WordNet antonyms or negation), commonsense context retrieval (COMET/ConceptNet), and ranking by contradiction score from an MNLI-trained RoBERTa.
  • Evaluation covered 150 non-sarcastic inputs, rated on Amazon Mechanical Turk across four criteria.
  • The full model (FM) won 90% of comparisons against Mishra et al. (2019) and 34% against human-written sarcasm. It was strongest on creativity, humor and sarcasticness and weaker on grammaticality.
  • Ablation: FM beat random selection of retrieved context (NSI) in 66% of the 119 non-tied cases. Human sarcasticness scores correlated more strongly with contradiction scores for FM than for NSI.
  • Limitations: the order of the two parts is fixed (context always comes after the flipped sentence), NLI scores are imperfect, and output quality depends on COMET. Code and data are available at github.com/tuhinjubcse/SarcasmGeneration-ACL2020.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cited by

32 papers of our library cite it (of the 140673 whose bibliographies we read); 7 of them have a page here, 25 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.acl-main.711

@inproceedings{chakrabarty2020r,
  title = {{R^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge}},
  author = {Chakrabarty, Tuhin and Ghosh, Debanjan and Muresan, Smaranda and Peng, Nanyun},
  booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
  year = {2020},
  doi = {10.18653/v1/2020.acl-main.711},
  url = {https://doi.org/10.18653/v1/2020.acl-main.711}
}

References

34 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Salvatore Attardo. 2000. Irony markers and functions: Towards a goal-oriented theory of irony and its processing. Rask, 12(1):3–20. find
  2. Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, and Yejin Choi. 2019. COMET: Commonsense transformers for automatic knowledge graph construction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4762–4779, Florence, Italy. Association for Computational Linguistics. find our card
  3. Samuel Bowman, Gabor Angeli, Christopher Potts, and Christopher D Manning. 2015. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 632–642. ↗
  4. Debanjan Ghosh, Alexander Richard Fabbri, and Smaranda Muresan. 2017. The role of conversation context for sarcasm detection in online interactions. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 186– 196, Saarbrücken, Germany. Association for Computational Linguistics. find our card
  5. Raymond W Gibbs. 1986. On the psycholinguistics of sarcasm. Journal of Experimental Psychology: General, 115(1):3. ↗
  6. Roberto González-Ibáñez, Smaranda Muresan, and Nina Wacholder. 2011. Identifying sarcasm in twitter: A closer look. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Short Papers - Volume 2, HLT ’11, pages 581–586, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
  7. Christian Burgers, Margot Van Mulken, and Peter Jan Schellens. 2012. Verbal irony differences in usage across written genres. Journal of Language and Social Psychology, 31(3):290–310. find
  8. Li Huang, Francesca Gino, and Adam Galinsky. 2015. The highest form of intelligence: Sarcasm increases creativity for both expressers and recipients. Organizational Behavior and Human Decision Processes, 131. ↗
  9. Dmitry Davidov, Oren Tsur, and Ari Rappoport. 2010. Semi-supervised recognition of sarcastic sentences in twitter and amazon. In In Proceedings of the Fourteenth Conference on Computational Natural Language Learning. CoNLL. find our card
  10. Aditya Joshi, Anoop Kunchukuttan, Pushpak Bhattacharyya, and Mark James Carman. 2015a. Sarcasmbot: An open-source sarcasm-generation module for chatbots. In WISDOM Workshop at KDD. find
  11. Andrea Esuli and Fabrizio Sebastiani. 2006. Sentiwordnet: A publicly available lexical resource for opinion mining. In LREC, volume 6, pages 417–422. Citeseer. find our card
  12. Zhenxin Fu, Xiaoye Tan, Nanyun Peng, Dongyan Zhao, and Rui Yan. 2017. Style transfer in text: Exploration and evaluation. In Proceedings of AAAI. find our card
  13. Aniruddha Ghosh and Tony Veale. 2017. Magnets for sarcasm: Making sarcasm detection timely, contextual and very personal. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 482–491, Copenhagen, Denmark. Association for Computational Linguistics. find our card
  14. Debanjan Ghosh, Alexander R Fabbri, and Smaranda Muresan. 2018. Sarcasm analysis using conversation context. Computational Linguistics, 44(4):755– 792. ↗ our card
  15. Debanjan Ghosh, Weiwei Guo, and Smaranda Muresan. 2015. Sarcastic or not: Word embeddings to predict the literal or sarcastic meaning of words. In proceedings of the 2015 conference on empirical methods in natural language processing, pages 1003–1012. find our card
  16. Debanjan Ghosh, Elena Musi, Kartikeya Upasani, and Smaranda Muresan. 2020. Interpreting verbal irony: Linguistic strategies and the connection to the type of semantic incongruity. Proceedings of the Society for Computation in Linguistics, 3(9):76–87. ↗
  17. Aditya Joshi, Vinita Sharma, and Pushpak Bhattacharyya. 2015b. Harnessing context incongruity for sarcasm detection. In ACL, pages 757–762. find our card
  18. Roger J Kreuz and Kristen E Link. 2002. Asymmetries in the use of verbal irony. Journal of Language and Social Psychology, 21(2):127–143. ↗
  19. Juncen Li, Robin Jia, He He, and Percy Liang. 2018. Delete, retrieve, generate: a simple approach to sentiment and style transfer. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1865–1874. ↗ our card
  20. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. ↗
  21. George A Miller. 1995. Wordnet: a lexical database for english. Communications of the ACM, 38(11):39– 41. ↗ our card
  22. Abhijit Mishra, Tarun Tater, and Karthik Sankaranarayanan. 2019. A modular architecture for unsupervised sarcasm generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6146–6155, Hong Kong, China. Association for Computational Linguistics. find our card
  23. Smaranda Muresan, Roberto Gonzalez-Ibanez, Debanjan Ghosh, and Nina Wacholder. 2016. Identification of nonliteral language in social media: A case study on sarcasm. Journal of the Association for Information Science and Technology, 67(11):2725– 2737. ↗
  24. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting on association for computational linguistics, pages 311–318. Association for Computational Linguistics. Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1112–1122. Association for Computational Linguistics. find our card
  25. Wei Zhao, Liang Wang, Kewei Shen, Ruoyu Jia, and Jingming Liu. 2019. Improving grammatical error correction via pre-training a copy-augmented architecture with unlabeled data. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 156–165. ↗
  26. Lotem Peled and Roi Reichart. 2017. Sarcasm SIGN: Interpreting sarcasm with sentiment based monolingual machine translation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1690–1700, Vancouver, Canada. Association for Computational Linguistics. find our card
  27. Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. In URL https://s3-us-west-2.amazonaws. com/openai-assets/researchcovers/languageunsupervised/language understanding paper. pdf. ↗
  28. Stefanie Regel. 2009. The comprehension of figurative language: electrophysiological evidence on the processing of irony. Ph.D. thesis, Max Planck Institute for Human Cognitive and Brain Sciences Leipzig. find
  29. Ellen Riloff, Ashequl Qadir, Prafulla Surve, Lalindra De Silva, Nathan Gilbert, and Ruihong Huang. 2013. Sarcasm as contrast between a positive sentiment and negative situation. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 704–714. find our card
  30. Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola. 2017. Style transfer from non-parallel text by cross-alignment. In Advances in neural information processing systems, pages 6830–6841. ↗ our card
  31. Stephen Skalicky and Scott Crossley. 2018. Linguistic features of sarcasm and metaphor production quality. In Proceedings of the Workshop on Figurative Language Processing, pages 7–16. find
  32. Robyn Speer, Joshua Chin, and Catherine Havasi. 2017. Conceptnet 5.5: An open multilingual graph of general knowledge. In Thirty-First AAAI Conference on Artificial Intelligence. ↗
  33. Cynthia Van Hee, Els Lefever, and Véronique Hoste. 2018. We usually dont like going to the dentist: Using common sense to detect irony on twitter. Computational Linguistics, 44(4):793–832. ↗ our card
  34. Adina Williams, Nikita Nangia, and Samuel Bowman. 2018. A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/chakrabarty-2020-r-textasciicircum3-reverse-retrieve-rank/