paper-with-me

홈 › Papers

Reversing Gradients in Adversarial Domain Adaptation for Question Deduplication and Textual Entailment Tasks

2019-07-01 · ACL 2019 7 · Anush Kamath, Sparsh Gupta, Vitor Carvalho

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationNatural Language InferenceRTE

Similar Papers 제목 키워드 기반

CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation

2023-04-19 · Chirag P, Mukta Wagle, Ravi Kant Gupta, Pranav Jeevan 외

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 Adaptation

Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training

2020-03-30 · ICLR 2020 1 · Jianfei Yang, Han Zou, Yuxun Zhou, Lihua Xie

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 Selection

Multi-Adversarial Domain Adaptation

2018-09-04 · Zhongyi Pei, Zhangjie Cao, Mingsheng Long, Jian-Min Wang

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 Adaptation

Gradient Distribution Alignment Certificates Better Adversarial Domain Adaptation

2021-01-01 · ICCV 2021 10 · Zhiqiang Gao, Shufei Zhang, Kaizhu Huang, Qiufeng Wang 외

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 Adaptation

Adversarial Domain Adaptation for Machine Reading Comprehension

2019-08-24 · IJCNLP 2019 11 · Huazheng Wang, Zhe Gan, Xiaodong Liu, Jingjing Liu 외

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