---
title: "Latent-Optimized Adversarial Neural Transfer for Sarcasm"
description: "Sarcasm detection suffers from a data split. 10.02 points. 63 references, cited by 3 papers here."
authors: ["Xu Guo", "Boyang Li", "Han Yu", "Chunyan Miao"]
year: 2021
venue: "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"
source: "https://aclanthology.org/2021.naacl-main.425/"
doi: "10.18653/v1/2021.naacl-main.425"
arxiv: "2104.09261"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/guo-2021-latent-optimized-adversarial-neural-transfer/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/guo-2021-latent-optimized-adversarial-neural-transfer/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/5/) / Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection

# Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection

**Authors:** Xu Guo, [Boyang Li](https://md.research.elamur.ai/free/en/authors/boyang-li/), Han Yu and [Chunyan Miao](https://md.research.elamur.ai/free/en/authors/chunyan-miao/) · **Year:** 2021 · **Venue:** [Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies](https://md.research.elamur.ai/free/en/venues/naacl/) ([NAACL 2021](https://md.research.elamur.ai/free/en/venues/naacl/2021/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2021.naacl-main.425/) · [PDF](https://aclanthology.org/2021.naacl-main.425.pdf) · [DOI 10.18653/v1/2021.naacl-main.425](https://doi.org/10.18653/v1/2021.naacl-main.425) · [arXiv 2104.09261](https://arxiv.org/abs/2104.09261) · [OpenAlex](https://openalex.org/W3167355120)

**Citations:** 24 citations (OpenAlex, 2026-10-14) · [3](https://md.research.elamur.ai/free/en/papers/guo-2021-latent-optimized-adversarial-neural-transfer/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Sarcasm detection suffers from a data split. Hand-labelled corpora such as SemEval-18 and iSarcasm are clean but contain only a few thousand texts. Hashtag-harvested corpora such as Ptáček and Ghosh are large but noisy. The authors transfer knowledge from the large noisy sets to the small clean ones using adversarial neural transfer (ANT). In ANT, a BERT encoder feeds domain-specific and shared dense layers, and a domain discriminator pushes the shared features of both domains to look alike.

They argue that the per-domain classification losses and the adversarial loss can pull against each other. This can leave the classifiers ignoring the shared features, so nothing is transferred. Their fix, LOANT, takes one look-ahead gradient step on the BERT output vectors, against the domain discrimination loss, before computing the task losses. Each task loss therefore has to adapt to the adversarial objective.

LOANT reaches a new state-of-the-art F-score of 46.41% on iSarcasm, 10.02 points above the previous best, and improves SemEval-18 by 3.08 points. This shows that small sarcasm benchmarks can profit from large, imperfect corpora.

## Key points
- The setup has two source corpora (Ptáček, Ghosh), both collected by distant supervision with hashtags, and two human-annotated targets (SemEval-18, iSarcasm), giving four transfer pairs. The authors describe this as the first transfer study across sarcasm datasets.
- Across the four pairs, latent optimization adds 3.42 F-score points on average over plain ANT and 4.83 over an ANT+MAML variant. MTL+LO beats MTL by 2.63 points, while plain ANT beats MTL by only 0.9 points and loses 0.56 points on Ptáček → SemEval-18.
- Doing the look-ahead in BERT parameter space (ANT+MAML) is 1.40 points worse than ANT on average. It also roughly doubles memory and runs about 3.1× longer than LOANT, whereas LO in latent space barely changes memory use.
- Domain similarity was measured by KL divergence of unigram distributions over shared vocabulary. Ptáček → iSarcasm is the closest pair (0.0521) and shows the largest LOANT gain over ANT (7.85 points).
- Fine-tuned BERT alone did not always beat task-specific LSTM models, which the authors attribute to overfitting on tiny datasets. Code and data are released at github.com/guoxuxu/LOANT.

## Interesting ideas
- Instead of trusting noisy hashtag labels outright, the model learns from both corpora jointly, keeping separate private and shared feature channels so noise in the big set does not dictate the small clean task.
- When several training objectives fight, nudge the intermediate representation one gradient step toward the adversary first, then optimize the task loss on the nudged vector; each objective must then hold up under the other's pressure.
- Doing the look-ahead on encoder outputs rather than on model weights keeps memory almost flat, so the trick stays cheap even with a huge pretrained encoder.
- A cheap unigram KL-divergence score between corpora predicted which source would help a target most.
- Comparing ANT with MTL showed that an added adversarial component can contribute almost nothing, or even hurt. Each extra loss term needs its own ablation against a simpler baseline.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (frames): The irony module in prag could be trained on large distantly labelled sarcasm data alongside a small curated set, with separate private and shared channels so the curated set stays the authority.
- **I2** (tree): gparse, trained jointly on several treebanks with a dialect-invariance term, could apply this step on encoder outputs to ease loss conflicts without touching transformer weights.
- **I3** (learn): This is a budget-friendly option for any GPU training run in Mova where second-order, MAML-style updates on full parameters would be too costly.
- **I4** (learn): Before adding a silver corpus or a converted treebank to training, compute its divergence from the target domain to rank candidates and anticipate which transfers pay off.
- **I5** (learn): Mova's evaluation could routinely include "component removed" runs as a control, so extra training machinery is kept only when it measurably helps.

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

## Institutions

- [Nanyang Technological University](https://md.research.elamur.ai/free/en/universities/nanyang-technological-university/) — University, Singapore, Singapore · 73 works · 24,390 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

🧭 Topics (1): [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 608 works

## Cite

Cite as: Xu Guo, Boyang Li, Han Yu and Chunyan Miao. 2021. Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{guo2021latent,
  title = {{Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection}},
  author = {Xu Guo, Boyang Li, Han Yu and Chunyan Miao},
  booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year = {2021},
  doi = {10.18653/v1/2021.naacl-main.425},
  eprint = {2104.09261},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2021.naacl-main.425}
}
```

- [← previous Exploring Transitivity in Neural NLI Models through Veridicality](https://md.research.elamur.ai/free/en/papers/yanaka-2021-exploring-transitivity-neural-nli-models/)
- [next → Mispronunciation Detection in Non-native (L2) English with Uncertainty Modeling](https://md.research.elamur.ai/free/en/papers/korzekwa-2021-mispronunciation-detection-non-native-l2/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/5/)

## References

63 references, 32 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Gavin Abercrombie and Dirk Hovy. 2016. [Putting sarcasm detection into context: The effects of class imbalance and manual labelling on supervised machine classification of twitter conversations](https://md.research.elamur.ai/free/en/papers/abercrombie-2016-putting-sarcasm-detection-into-context/). In Proceedings of the ACL 2016 student research workshop, pages 107–113.
2. Roee Aharoni, Melvin Johnson, and Orhan Firat. 2019. [Massively multilingual neural machine translation](https://md.research.elamur.ai/free/en/papers/aharoni-2019-massively-multilingual-neural-machine-translation/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. [↗](https://doi.org/10.48550/arxiv.1903.00089)
3. Héctor Martínez Alonso and Barbara Plank. 2017. When is multitask learning effective? semantic sequence prediction under varying data conditions. In EACL. [↗](https://doi.org/10.48550/arxiv.1612.02251)
4. Silvio Amir, Byron C. Wallace, Hao Lyu, and Paula Carvalho Mário J. Silva. 2016. [Modelling context with user embeddings for sarcasm detection in social media](https://md.research.elamur.ai/free/en/papers/amir-2016-modelling-context-user-embeddings-sarcasm/). In CoNLL.
5. Waïss Azizian, Ioannis Mitliagkas, Simon Lacoste-Julien, and Gauthier Gidel. 2020. A tight and unified analysis of gradient-based methods for a whole spectrum of games. In AISTATS. [↗](https://doi.org/10.48550/arxiv.1906.05945)
6. David Balduzzi, Sébastien Racanière, James Martens, Jakob N. Foerster, Karl Tuyls, and Thore Graepel. 2018. The mechanics of n-player differentiable games. In ICML. [↗](https://doi.org/10.48550/arxiv.1802.05642)
7. David Bamman and Noah A Smith. 2015. Contextualized sarcasm detection on twitter. In Ninth international AAAI conference on web and social media. Citeseer. [find](https://scholar.google.com/scholar?q=David+Bamman+and+Noah+A+Smith%2E+2015%2E+Contextualized+sarcasm+detection+on+twitter%2E+In+Ninth+international+AAAI+conference+on+web+and+social+media%2E+Citeseer%2E)
8. Christos Baziotis, Nikos Pelekis, and Christos Doulk-eridis. 2017. [Datastories at SemEval-2017 task 4: Deep LSTM with attention for message-level and topic-based sentiment analysis](https://md.research.elamur.ai/free/en/papers/baziotis-2017-datastories-semeval-2017-task-4/). In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 747–754, Vancouver, Canada. Association for Computational Linguistics.
9. Shai Ben-David, John Blitzer, Koby Crammer, Alex Kulesza, Fernando Pereira, and Jennifer Wortman Vaughan. 2010. A theory of learning from different domains. Machine learning, 79(1):151–175. [↗](https://doi.org/10.1007/s10994-009-5152-4)
10. Joachim Bingel and Anders Søgaard. 2017. [Identifying beneficial task relations for multi-task learning in deep neural networks](https://md.research.elamur.ai/free/en/papers/bingel-2017-identifying-beneficial-task-relations-multi/). In EACL.
11. Xilun Chen, Yu Sun, Ben Athiwaratkun, Claire Cardie, and Kilian Weinberger. 2018. [Adversarial deep averaging networks for cross-lingual sentiment classification](https://md.research.elamur.ai/free/en/papers/chen-2018-adversarial-deep-averaging-networks-cross/). Transactions of the Association for Computational Linguistics, 6:557–570. [↗](https://doi.org/10.1162/tacl_a_00039)
12. Kevin Clark, Minh-Thang Luong, Urvashi Khandelwal, Christopher D. Manning, and Quoc V. Le. 2019. [Bam! born-again multi-task networks for natural language understanding](https://md.research.elamur.ai/free/en/papers/clark-2019-bam-born-again-multi-task/). In ACL.
13. Ronan Collobert, Jason Weston, Leon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. [Natural language processing (almost) from scratch](https://md.research.elamur.ai/free/en/papers/collobert-2011-natural-language-processing-almost-scratch/). JMLR, 12:2493–2537.
14. Dmitry Davidov, Oren Tsur, and Ari Rappoport. 2010. [Semi-supervised recognition of sarcastic sentences in twitter and amazon](https://md.research.elamur.ai/free/en/papers/davidov-2010-semi-supervised-recognition-sarcasm-twitter/). In Proceedings of the Fourteenth Conference on Computational Natural Language Learning, page 107–116, USA. Association for Computational Linguistics.
15. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [BERT: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). 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 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/n19-1423)
16. Bjarke Felbo, Alan Mislove, Anders Søgaard, Iyad Rahwan, and Sune Lehmann. 2017. [Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm](https://md.research.elamur.ai/free/en/papers/felbo-2017-millions-emoji-occurrences-learn-any/). In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1615–1625, Copenhagen, Denmark. Association for Computational Linguistics.
17. Elena Filatova. 2012. [Irony and sarcasm: Corpus generation and analysis using crowdsourcing](https://md.research.elamur.ai/free/en/papers/filatova-2012-irony-sarcasm-corpus-generation-analysis/). In Proceedings of the Eighth International Conference on Language Resources and Evaluation, Istanbul, Turkey.
18. Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 1126–1135. PMLR. [↗](https://doi.org/10.48550/arxiv.1703.03400)
19. Yitao Cai, Huiyu Cai, and Xiaojun Wan. 2019. [Multimodal sarcasm detection in Twitter with hierarchical fusion model](https://md.research.elamur.ai/free/en/papers/cai-2019-multi-modal-sarcasm-detection-twitter/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2506–2515, Florence, Italy. Association for Computational Linguistics.
20. Jean E. Fox Tree, J. Trevor D’Arcey, Alicia A. Hammond, and Alina S. Larson. 2020. The sarchasm: Sarcasm production and identification in spontaneous conversation. Discourse Processes, 57(5-6):507–533. [↗](https://doi.org/10.1080/0163853x.2020.1759016)
21. Soravit Changpinyo, Hexiang Hu, and Fei Sha. 2018. Multi-task learning for sequence tagging: An empirical study. In COLING. [↗](https://doi.org/10.48550/arxiv.1808.04151)
22. Yaroslav Ganin and Victor Lempitsky. 2015. Unsupervised domain adaptation by backpropagation. In ICML, volume 37, pages 1180–1189. [↗](https://doi.org/10.48550/arxiv.1409.7495)
23. Ian Gemp and Sridhar Mahadevan. 2019. Global convergence to the equilibrium of gans using variational inequalities. arXiv 1808.01531. [↗](https://arxiv.org/abs/1808.01531)
24. Aniruddha Ghosh and Tony Veale. 2016. [Fracking sarcasm using neural network](https://md.research.elamur.ai/free/en/papers/ghosh-2016-fracking-sarcasm-neural-network/). In Proceedings of the 7th workshop on computational approaches to subjectivity, sentiment and social media analysis, pages 161–169. [↗](https://doi.org/10.13140/rg.2.2.16560.15363)
25. Raymond W. Gibbs. 2000. Irony in talk among friends. Metaphor and Symbol, 15(1-2):5–27. [↗](https://doi.org/10.1207/s15327868ms151&2_2)
26. Roberto González-Ibáñez, Smaranda Muresan, and Nina Wacholder. 2011. [Identifying sarcasm in Twitter: A closer look](https://md.research.elamur.ai/free/en/papers/ibanez-2011-identifying-sarcasm-twitter-closer-look/). In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies.
27. Roberto González-Ibánez, Smaranda Muresan, and Nina Wacholder. 2011. [Identifying sarcasm in twitter: a closer look](https://md.research.elamur.ai/free/en/papers/ibanez-2011-identifying-sarcasm-twitter-closer-look/). In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 581–586.
28. Han Guo, Ramakanth Pasunuru, and Mohit Bansal. 2019. Autosem: Automatic task selection and mixing in multi-task learning. In NAACL. [↗](https://doi.org/10.48550/arxiv.1904.04153)
29. Aditya Joshi, Vinita Sharma, and Pushpak Bhattacharyya. 2015. [Harnessing context incongruity for sarcasm detection](https://md.research.elamur.ai/free/en/papers/joshi-2015-harnessing-context-incongruity-sarcasm-detection/). In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 757–762.
30. Anush Kamath, Sparsh Gupta, and Vitor Carvalho. 2019. Reversing gradients in adversarial domain adaptation for question deduplication and textual entailment tasks. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5545–5550. [find](https://scholar.google.com/scholar?q=Anush+Kamath%2C+Sparsh+Gupta%2C+and+Vitor+Carvalho%2E+2019%2E+Reversing+gradients+in+adversarial+domain+adaptation+for+question+deduplication+and+textual+entailment+tasks%2E+In+Proceedings+of+the+57th+Annual+Me)
31. Sandeepa Kannangara. 2018. Mining twitter for fine-grained political opinion polarity classification, ideology detection and sarcasm detection. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pages 751–752. [find](https://scholar.google.com/scholar?q=Sandeepa+Kannangara%2E+2018%2E+Mining+twitter+for+fine%2Dgrained+political+opinion+polarity+classification%2C+ideology+detection+and+sarcasm+detection%2E+In+Proceedings+of+the+Eleventh+ACM+International+Confere)
32. Mikhail Khodak, Nikunj Saunshi, and Kiran Vodrahalli. 2018a. [A large self-annotated corpus for sarcasm](https://md.research.elamur.ai/free/en/papers/khodak-2018-large-self-annotated-corpus-sarcasm/). In Proceedings of the Eighth International Conference on Language Resources and Evaluation.
33. Mikhail Khodak, Nikunj Saunshi, and Kiran Vodrahalli. 2018b. [A large self-annotated corpus for sarcasm](https://md.research.elamur.ai/free/en/papers/khodak-2018-large-self-annotated-corpus-sarcasm/). In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA).
34. Young-Bum Kim, Karl Stratos, and Dongchan Kim. 2017. Adversarial adaptation of synthetic or stale data. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1297–1307. [find](https://scholar.google.com/scholar?q=Young%2DBum+Kim%2C+Karl+Stratos%2C+and+Dongchan+Kim%2E+2017%2E+Adversarial+adaptation+of+synthetic+or+stale+data%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volu)
35. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. [↗](https://arxiv.org/abs/1412.6980)
36. G. M. Korpelevich. 1976. An extragradient method for finding saddle points and for other problems. Ekonomika i Matematicheskie Metody, 12:747–756. [find](https://scholar.google.com/scholar?q=G%2E+M%2E+Korpelevich%2E+1976%2E+An+extragradient+method+for+finding+saddle+points+and+for+other+problems%2E+Ekonomika+i+Matematicheskie+Metody%2C+12%3A747%E2%80%93756%2E)
37. Roger Kreuz and Gina Caucci. 2007. [Lexical influences on the perception of sarcasm](https://md.research.elamur.ai/free/en/papers/kreuz-2007-lexical-influences-perception-sarcasm/). In Proceedings of the Workshop on Computational Approaches to Figurative Language, pages 1–4, Rochester, New York. Association for Computational Linguistics.
38. Pengfei Liu, Xipeng Qiu, and Xuanjing Huang. 2017. [Adversarial multi-task learning for text classification](https://md.research.elamur.ai/free/en/papers/liu-2017-adversarial-multi-task-learning-text/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1–10, Vancouver, Canada. Association for Computational Linguistics.
39. Qi Liu, Yue Zhang, and Jiangming Liu. 2018. Learning domain representation for multi-domain sentiment classification. 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 541–550. [find](https://scholar.google.com/scholar?q=Qi+Liu%2C+Yue+Zhang%2C+and+Jiangming+Liu%2E+2018%2E+Learning+domain+representation+for+multi%2Ddomain+sentiment+classification%2E+In+Proceedings+of+the+2018+Conference+of+the+North+American+Chapter+of+the+Associa)
40. Diana G Maynard and Mark A Greenwood. 2014. [Who cares about sarcastic tweets? investigating the impact of sarcasm on sentiment analysis](https://md.research.elamur.ai/free/en/papers/maynard-2014-who-cares-about-sarcastic-tweets/). In LREC 2014 Proceedings. ELRA.
41. Robert McHardy, Heike Adel, and Roman Klinger. 2019. Adversarial training for satire detection: Controlling for confounding variables. 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 660–665, Minneapolis, Minnesota. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Robert+McHardy%2C+Heike+Adel%2C+and+Roman+Klinger%2E+2019%2E+Adversarial+training+for+satire+detection%3A+Controlling+for+confounding+variables%2E+In+Proceedings+of+the+2019+Conference+of+the+North+American+Chapt)
42. Luke Metz, Ben Poole, David Pfau, and Jascha Sohl-Dickstein. 2016. Unrolled generative adversarial networks. In NeurIPS. [↗](https://doi.org/10.48550/arxiv.1611.02163)
43. Abhijit Mishra, Kuntal Dey, and Pushpak Bhattacharyya. 2017. [Learning cognitive features from gaze data for sentiment and sarcasm classification using convolutional neural network](https://md.research.elamur.ai/free/en/papers/mishra-2017-learning-cognitive-features-gaze-data/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
44. Silviu Oprea and Walid Magdy. 2020. [isarcasm: A dataset of intended sarcasm](https://md.research.elamur.ai/free/en/papers/oprea-2020-isarcasm-dataset-intended-sarcasm/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics.
45. Shereen Oraby, Vrindavan Harrison, Lena Reed, Ernesto Hernandez, Ellen Riloff, and Marilyn Walker. 2016. [Creating and characterizing a diverse corpus of sarcasm in dialogue](https://md.research.elamur.ai/free/en/papers/oraby-2016-creating-characterizing-diverse-corpus-sarcasm/). In Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 31–41, Los Angeles. Association for Computational Linguistics.
46. Chuhan Wu, Fangzhao Wu, Sixing Wu, Junxin Liu, Zhigang Yuan, and Yongfeng Huang. 2018. Thu_ngn at SemEval-2018 task 3: Tweet irony detection with densely connected LSTM and multi-task learning. In Proceedings of The 12th International Workshop on Semantic Evaluation, pages 51– 56. [find](https://scholar.google.com/scholar?q=Chuhan+Wu%2C+Fangzhao+Wu%2C+Sixing+Wu%2C+Junxin+Liu%2C+Zhigang+Yuan%2C+and+Yongfeng+Huang%2E+2018%2E+Thu%5Fngn+at+SemEval%2D2018+task+3%3A+Tweet+irony+detection+with+densely+connected+LSTM+and+multi%2Dtask+learning%2E+In+Pro)
47. Tomáš Ptáček, Ivan Habernal, and Jun Hong. 2014. [Sarcasm detection on Czech and English twitter](https://md.research.elamur.ai/free/en/papers/ptacek-2014-sarcasm-detection-czech-english-twitter/). In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pages 213–223.
48. Yan Wu, Jeff Donahue, David Balduzzi, Karen Simonyan, and Timothy Lillicrap. 2019a. Logan: Latent optimisation for generative adversarial networks. arXiv preprint arXiv:1912.00953. [↗](https://arxiv.org/abs/1912.00953)
49. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Journal of Machine Learning Research, 21(140):1–67. [↗](https://doi.org/10.48550/arxiv.1910.10683)
50. Ashwin Rajadesingan, Reza Zafarani, and Huan Liu. 2015. Sarcasm detection on twitter: A behavioral modeling approach. In Proceedings of the eighth ACM international conference on web search and data mining, pages 97–106. [↗](https://doi.org/10.1145/2684822.2685316)
51. Ellen Riloff, Ashequl Qadir, Prafulla Surve, Lalin-draDe Silva, Nathan Gilbert, and Ruihong Huang. 2013. Sarcasm as contrast between a positive sen-timentand negative situation. In EMNLP. [find](https://scholar.google.com/scholar?q=Ellen+Riloff%2C+Ashequl+Qadir%2C+Prafulla+Surve%2C+Lalin%2DdraDe+Silva%2C+Nathan+Gilbert%2C+and+Ruihong+Huang%2E+2013%2E+Sarcasm+as+contrast+between+a+positive+sen%2Dtimentand+negative+situation%2E+In+EMNLP%2E)
52. Yi Tay, Anh Tuan Luu, Siu Cheung Hui, and Jian Su. 2018. [Reasoning with sarcasm by reading in-between](https://md.research.elamur.ai/free/en/papers/tay-2018-reasoning-sarcasm-reading-between/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1010–1020, Melbourne, Australia. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/p18-1093)
53. Joseph Tepperman, David Traum, and Shrikanth Narayanan. 2006. " yeah right": Sarcasm recognition for spoken dialogue systems. In Ninth international conference on spoken language processing. [find](https://scholar.google.com/scholar?q=Joseph+Tepperman%2C+David+Traum%2C+and+Shrikanth+Narayanan%2E+2006%2E+%22+yeah+right%22%3A+Sarcasm+recognition+for+spoken+dialogue+systems%2E+In+Ninth+international+conference+on+spoken+language+processing%2E)
54. Cynthia Van Hee, Els Lefever, and Véronique Hoste. 2018. [Semeval-2018 task 3: Irony detection in english tweets](https://md.research.elamur.ai/free/en/papers/hee-2018-semeval-2018-task-3-irony/). In Proceedings of The 12th International Workshop on Semantic Evaluation, pages 39– 50.
55. Yan Wu, Mihaela Rosca, and Timothy Lillicrap. 2019b. Deep compressed sensing. In Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 6850–6860. PMLR. [↗](https://doi.org/10.48550/arxiv.1905.06723)
56. Tao Xiong, Peiran Zhang, Hongbo Zhu, and Yihui Yang. 2019. Sarcasm detection with self-matching networks and low-rank bilinear pooling. In The World Wide Web Conference, pages 2115–2124. [find](https://scholar.google.com/scholar?q=Tao+Xiong%2C+Peiran+Zhang%2C+Hongbo+Zhu%2C+and+Yihui+Yang%2E+2019%2E+Sarcasm+detection+with+self%2Dmatching+networks+and+low%2Drank+bilinear+pooling%2E+In+The+World+Wide+Web+Conference%2C+pages+2115%E2%80%932124%2E)
57. Zhilin Yang, Ruslan Salakhutdinov, and William W. Cohen. 2017. Transfer learning for sequence tagging with hierarchical recurrent networks. In ICLR. [↗](https://doi.org/10.48550/arxiv.1703.06345)
58. Jianfei Yu, Minghui Qiu, Jing Jiang, Jun Huang, Shuangyong Song, Wei Chu, and Haiqing Chen. 2018. Modelling domain relationships for transfer learning on retrieval-based question answering systems in e-commerce. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining. [find](https://scholar.google.com/scholar?q=Jianfei+Yu%2C+Minghui+Qiu%2C+Jing+Jiang%2C+Jun+Huang%2C+Shuangyong+Song%2C+Wei+Chu%2C+and+Haiqing+Chen%2E+2018%2E+Modelling+domain+relationships+for+transfer+learning+on+retrieval%2Dbased+question+answering+systems+in+)
59. Meishan Zhang, Yue Zhang, and Guohong Fu. 2016. [Tweet sarcasm detection using deep neural network](https://md.research.elamur.ai/free/en/papers/zhang-2016-tweet-sarcasm-detection-deep-neural/). In Proceedings of COLING 2016, The 26th International Conference on Computational Linguistics: Technical Papers, pages 2449–2460.
60. Joey Tianyi Zhou, Hao Zhang, Di Jin, Hongyuan Zhu, Meng Fang, Rick Siow Mong Goh, and Kenneth Kwok. 2019. Dual adversarial neural transfer for low-resource named entity recognition. In ACL, pages 3461–3471. [find](https://scholar.google.com/scholar?q=Joey+Tianyi+Zhou%2C+Hao+Zhang%2C+Di+Jin%2C+Hongyuan+Zhu%2C+Meng+Fang%2C+Rick+Siow+Mong+Goh%2C+and+Kenneth+Kwok%2E+2019%2E+Dual+adversarial+neural+transfer+for+low%2Dresource+named+entity+recognition%2E+In+ACL%2C+pages+3461)
61. Tony Veale, F Amílcar Cardoso, and Rafael Pérez y Pérez. 2019. Systematizing creativity: A computational view. In Computational Creativity, pages 1–19. Springer. [↗](https://doi.org/10.1007/978-3-319-43610-4_1)
62. Marilyn A Walker, Jean E Fox Tree, Pranav Anand, Rob Abbott, and Joseph King. 2012. [A corpus for research on deliberation and debate](https://md.research.elamur.ai/free/en/papers/walker-2012-corpus-research-deliberation-debate/). In LREC, volume 12, pages 812–817. Istanbul.
63. Byron C Wallace, Laura Kertz, Eugene Charniak, et al. 2014. [Humans require context to infer ironic intent (so computers probably do, too)](https://md.research.elamur.ai/free/en/papers/wallace-2014-humans-require-context-infer-ironic/). In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 512–516.

*Updated 24 October 2026*