mlsanityData to 7 Oct 2026

Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection

arXiv 2104.09261 ↗First posted 19 Apr 2021cs.LG cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

The existence of multiple datasets for sarcasm detection prompts us to apply transfer learning to exploit their commonality. The adversarial neural transfer (ANT) framework utilizes multiple loss terms that encourage the source-domain and the target-domain feature distributions to be similar while optimizing for domain-specific performance. However, these objectives may be in conflict, which can lead to optimization difficulties and sometimes diminished transfer. We propose a generalized latent optimization strategy that allows different losses to accommodate each other and improves training dynamics. The proposed method outperforms transfer learning and meta-learning baselines. In particular, we achieve 10.02% absolute performance gain over the previous state of the art on the iSarcasm dataset.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 28 of its 63 references that are in the map. First posted on arXiv 19 Apr 2021.

Builds on

28 of 63 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  6. 2019Massively Multilingual Neural Machine Translationcited by 246
  7. 2018The Natural Language Decathlon: Multitask Learning as Question Answeringcited by 235
  8. 2016Unrolled Generative Adversarial Networkscited by 208
  9. 2018The Mechanics of n-Player Differentiable Gamescited by 118
  10. 2017Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasmcited by 117
  11. 2017Adversarial Multi-task Learning for Text Classificationcited by 91
  12. 2019BAM! Born-Again Multi-Task Networks for Natural Language Understandingcited by 85
16 more
  1. 2017A Large Self-Annotated Corpus for Sarcasmcited by 63
  2. 2017Identifying beneficial task relations for multi-task learning in deep neural networkscited by 59
  3. 2016Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classificationcited by 48
  4. 2019Deep Compressed Sensingcited by 46
  5. 2017Creating and Characterizing a Diverse Corpus of Sarcasm in Dialoguecited by 42
  6. 2019LOGAN: Latent Optimisation for Generative Adversarial Networkscited by 42
  7. 2019iSarcasm: A Dataset of Intended Sarcasmcited by 39
  8. 2018Reasoning with Sarcasm by Reading In-betweencited by 38
  9. 2017Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networkscited by 30
  10. 2016Modelling Context with User Embeddings for Sarcasm Detection in Social Mediacited by 26
  11. 2019AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learningcited by 22
  12. 2016When is multitask learning effective? Semantic sequence prediction under varying data conditionscited by 21
  13. 2017Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commercecited by 18
  14. 2018Global Convergence to the Equilibrium of GANs using Variational Inequalitiescited by 15
  15. 2018Multi-Task Learning for Sequence Tagging: An Empirical Studycited by 15
  16. 2019Adversarial Training for Satire Detection: Controlling for Confounding Variablescited by 13

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 4; 2023: 0; 2024: 1.

6 papers.

  1. 2024Generative AI for Synthetic Data Generation: Methods, Challenges and the Futurecited by 31
  2. 2022On the Domain Adaptation and Generalization of Pretrained Language Models: A Surveycited by 22
  3. 2022Improving the Sample Efficiency of Prompt Tuning with Domain Adaptationcited by 15
  4. 2022A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculturecited by 6
  5. 2022UTNLP at SemEval-2022 Task 6: A Comparative Analysis of Sarcasm Detection Using Generative-based and Mutation-based Data Augmentationcited by 5
  6. 2021Sarcasm Detection in Twitter -- Performance Impact while using Data Augmentation: Word Embeddingscited by 0