Adversarial Training for Satire Detection: Controlling for Confounding Variables

McHardy, Robert J.; Adel, Heike; Klinger, Roman

doi:10.48550/arxiv.1902.11145

Cited by 3 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4 It is a liter-ary device that writers use to mock or ridicule a person, group, or ideology by judging them for various issues, particularly in the context of contemporary politics and other topical issues [109]. Such devices include humor, irony, sarcasm, exaggerations, parody, or caricature [110]. These are typically applied to news and social media posts and the purpose is not to cause harm but to ridicule, or expose behavior that is shameful, corrupt, or otherwise "bad" [111,112,113].…”

Section: Satiresmentioning

confidence: 99%

See 1 more Smart Citation

Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directions

Alsmadi¹,

Ahmad²,

Nazzal³

et al. 2021

Preprint

View full text Add to dashboard Cite

The growing use of social media has led to the development of several Machine Learning (ML) and Natural Language Processing (NLP) tools to process the unprecedented amount of social media content to make actionable decisions. However, these ML and NLP algorithms have been widely shown to be vulnerable to adversarial attacks. These vulnerabilities allow adversaries to launch a diversified set of adversarial attacks on these algorithms in different applications of social media text processing. In this paper, we provide a comprehensive review of the main approaches for adversarial attacks and defenses in the context of social media applications with a particular focus on key challenges and future research directions. In detail, we cover literature on six key applications, namely (i) rumors detection, (ii) satires detection, (iii) clickbaits & spams identification, (iv) hate speech detection, (v) misinformation detection, and (vi) sentiment analysis. We then highlight the concurrent and anticipated future research questions and provide recommendations and directions for future work.

show abstract

Section: Satiresmentioning

confidence: 99%

“…Adversarial work: The work on adversarial training for satire detection is relatively new. The study in [110] used adversarial training while training the model, however, the purpose was not to defend an adversarial attack, rather the idea was to control the effect of publication source information in satire detection.…”

Section: Satiresmentioning

confidence: 99%

Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directions

Alsmadi¹,

Ahmad²,

Nazzal³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…These methods are usually limited to data in low feature space unlike speech or language representations. In the context of neural networks, controlling for confounding factors during training is commonly achieved via the adversarial training paradigm [13,16,30,33,36,46]. In this paradigm, a network learns how to perform a specific task (e.g., detect emotion) while at the same time "unlearns" how to perform another task (e.g., detect stress).…”

Section: Related Workmentioning

confidence: 99%

“…Meng et al [33] used adversarial multi-task learning to curtail variances due to speaker identity when training automatic speech recognition systems, demonstrating how controlling for such variations improves generalization performance. McHardy et al [31] used the same approach to prevent the network from learning publication source characteristics while being primarily trained for recognizing instances of satire. They demonstrated how classifiers trained to predict satire often predict publication source, by associating the publication source to the intended target label.…”

Section: Related Workmentioning

confidence: 99%

“…Adversarial multi-task learning was also used in other fields (e.g., computer vision, language processing) to train models that are invariant to certain properties, yet discriminative with respect to others [13,16,30]. Given a source domain and a target domain, the goal is to study how controlling for an extraneous confounding factor when training our emotion recognition models on the source domain affects the performance of the trained models on both source and target domains.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Controlling for Confounders in Multimodal Emotion Classification via Adversarial Learning

Jaiswal

Aldeneh

Provost

2019

2019 International Conference on Multimodal Interaction

View full text Add to dashboard Cite

Various psychological factors affect how individuals express emotions. Yet, when we collect data intended for use in building emotion recognition systems, we often try to do so by creating paradigms that are designed just with a focus on eliciting emotional behavior. Algorithms trained with these types of data are unlikely to function outside of controlled environments because our emotions naturally change as a function of these other factors. In this work, we study how the multimodal expressions of emotion change when an individual is under varying levels of stress. We hypothesize that stress produces modulations that can hide the true underlying emotions of individuals and that we can make emotion recognition algorithms more generalizable by controlling for variations in stress. To this end, we use adversarial networks to decorrelate stress modulations from emotion representations. We study how stress alters acoustic and lexical emotional predictions, paying special attention to how modulations due to stress affect the transferability of learned emotion recognition models across domains. Our results show that stress is indeed encoded in trained emotion classifiers and that this encoding varies across levels of emotions and across the lexical and acoustic modalities. Our results also show that emotion recognition models that control for stress during training have better generalizability when applied to new domains, compared to models that do not control for stress during training. We conclude that is is necessary to consider the effect of extraneous psychological factors when building and testing emotion recognition models.

show abstract

Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection

Guo¹,

et al. 2021

Preprint

View full text Add to dashboard Cite

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.

show abstract

Adversarial Training for Satire Detection: Controlling for Confounding Variables

Cited by 3 publications

References 0 publications

Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directions

Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directions

Controlling for Confounders in Multimodal Emotion Classification via Adversarial Learning

Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection

Contact Info

Product

Resources

About