Reversing Gradients in Adversarial Domain Adaptation for Question Deduplication and Textual Entailment Tasks
Adversarial domain adaptation has been recently proposed as an effective technique for textual matching tasks, such as question deduplication. Here we investigate the use of gradient reversal on adversarial domain adaptation to explicitly learn both shared and unshared (domain specific) representations between two textual domains. In doing so, gradient reversal learns features that explicitly compensate for domain mismatch, while still distilling domain specific knowledge that can improve target domain accuracy. We evaluate reversing gradients for adversarial adaptation on multiple domains, and demonstrate that it significantly outperforms other methods on question deduplication as well as on recognizing textual entailment (RTE) tasks, achieving up to 7{\%} absolute boost in base model accuracy on some datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationNatural Language InferenceRTESimilar Papers 제목 키워드 기반
CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation
We propose a new technique called CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation. Adversarial training is commonly used for learning domain-invariant representations by…
Domain AdaptationUnsupervised Domain AdaptationTowards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training
Domain adaptation tackles the problem of transferring knowledge from a label-rich source domain to a label-scarce or even unlabeled target domain. Recently domain-adversarial training (DAT) has shown promising capacity t…
Domain AdaptationModel SelectionMulti-Adversarial Domain Adaptation
Recent advances in deep domain adaptation reveal that adversarial learning can be embedded into deep networks to learn transferable features that reduce distribution discrepancy between the source and target domains. Exi…
Domain AdaptationGradient Distribution Alignment Certificates Better Adversarial Domain Adaptation
The latest heuristic for handling the domain shift in unsupervised domain adaptation tasks is to reduce the data distribution discrepancy using adversarial learning. Recent studies improve the conventional adversaria…
Domain AdaptationUnsupervised Domain AdaptationAdversarial Domain Adaptation for Machine Reading Comprehension
In this paper, we focus on unsupervised domain adaptation for Machine Reading Comprehension (MRC), where the source domain has a large amount of labeled data, while only unlabeled passages are available in the target dom…
Domain AdaptationMachine Reading ComprehensionReading ComprehensionRepresentation Learning+1