Adversarial Domain Adaptation for Stance Detection

Xu, Brian; Mohtarami, Mitra; Glass, James

doi:10.48550/arxiv.1902.02401

Cited by 6 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DANNs have been applied in a range of NLP applications in the last few years, mainly to sentiment classification (Ganin et al, 2016;Li et al, 2018a;Shen et al, 2018), but recently to many other tasks as well: language identification (Li et al, 2018a), relation extraction (Fu et al, 2017;Rios et al, 2018) and other (binary) text classification tasks like relevancy identification (Alam et al, 2018a), duplicate question detection (Shah et al, 2018), POS tagging (Yasunaga et al, 2018), parsing (Sato et al, 2017), stance detection (Xu et al, 2019). This makes DANNs the most widely used UDA approach in NLP, as illustrated in Table 1.…”

Section: Domain Adversariesmentioning

confidence: 99%

Neural Unsupervised Domain Adaptation in NLP---A Survey

Ramponi¹,

Plank²

2020

Preprint

View full text Add to dashboard Cite

Deep neural networks excel at learning from labeled data and achieve state-of-the-art results on a wide array of Natural Language Processing tasks. In contrast, learning from unlabeled data, especially under domain shift, remains a challenge. Motivated by the latest advances, in this survey we review neural unsupervised domain adaptation techniques which do not require labeled target domain data. This is a more challenging yet a more widely applicable setup. We outline methods, from early approaches in traditional non-neural methods to pre-trained model transfer. We also revisit the notion of domain, and we uncover a bias in the type of Natural Language Processing tasks which received most attention. Lastly, we outline future directions, particularly the broader need for out-of-distribution generalization of future intelligent NLP. 1

show abstract

Section: Domain Adversariesmentioning

confidence: 99%

Neural Unsupervised Domain Adaptation in NLP---A Survey

Ramponi¹,

Plank²

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…This dataset has greatly promoted the research on stance detection. Some work focuses on task settings where targets are the same between the training and test datasets [1], [2], [3], while other research explores transfer learning from one domain to another [8], [9], [10]. In the present study, we focus on transfer learning from multiple source domains to unseen target domains, which is more challenging because the model cannot learn features directly from target domains during training.…”

Section: A Stance Detectionmentioning

confidence: 99%

“…Xu et al [10] first introduce adversarial learning for stance detection to tackle the problem where there is limited labeled data in the target domain, but sufficient labeled data in the source domain, and experiment results show that their model outperforms their best baseline.…”

Section: B Adversarial Trainingmentioning

confidence: 99%

“…where 𝒔 𝐼𝑛𝑣𝑎𝑟 and 𝒔 𝑆𝑝𝑒𝑐 are sentence representations of domain-invariant and domain-specific models, respectively, which can be calculated using formulae (1)(2)(3)(4)(5)(6)(7)(8)(9)(10). Finally, we place the target classifier over 𝒔, and the subsequent process is the same as formulae (11) and (12).…”

Section: Domain Specific Representationsmentioning

confidence: 99%

“…Thus, during training, the resulting representations of BiLSTMs and attention layers will confuse target classifiers, keeping learned representations domaininvariant, and formula (22) tries to minimize the target We use the standard back-propagation method to train model parameters. To jointly implement formulae ( 21) and ( 22), we introduce a gradient reverse layer (GRL) between the sentence representation layer and the target classifier, in the same way as shown in the previous work on adversarial training [10].…”

Section: Trainingmentioning

confidence: 99%

See 2 more Smart Citations

Unseen Target Stance Detection with Adversarial Domain Generalization

Wang

et al. 2020

2020 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Although stance detection has made great progress in the past few years, it is still facing the problem of unseen targets. In this study, we investigate the domain difference between targets and thus incorporate attention-based conditional encoding with adversarial domain generalization to perform unseen target stance detection. Experimental results show that our approach achieves new state-of-the-art performance on the SemEval-2016 dataset, demonstrating the importance of domain difference between targets in unseen target stance detection.

show abstract

Domain Adaptation: Challenges, Methods, Datasets, and Applications

et al. 2023

View full text Add to dashboard Cite

Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well on another set of data (target domain), which is different but has similar properties as the source domain. Domain Adaptation (DA) strives to alleviate this problem and has great potential in its application in practical settings, real-world scenarios, industrial applications and many data domains. Various DA methods aimed at individual data domains have been reported in the last few years; however, there is no comprehensive survey that encompasses all these data domains, focuses on the datasets available, the methods relevant to each domain, and importantly the applications and challenges. To that end, this survey paper discusses how DA can help DNNs work efficiently in these settings by reviewing DA methods and techniques. We have considered five data domains: computer vision, natural language processing, speech, time-series, and multi-modal data. We present a comprehensive taxonomy, including the methods, datasets, challenges, and applications corresponding to each domain. Our goal is to discuss industrial use cases and DA implementation for those. Our final aim is to provide future research directions based on evolving methods and results, the datasets used, and industrial applications.

show abstract

Adversarial Domain Adaptation for Stance Detection

Cited by 6 publications

References 0 publications

Neural Unsupervised Domain Adaptation in NLP---A Survey

Neural Unsupervised Domain Adaptation in NLP---A Survey

Unseen Target Stance Detection with Adversarial Domain Generalization

Domain Adaptation: Challenges, Methods, Datasets, and Applications

Contact Info

Product

Resources

About