Fast Easy Unsupervised Domain Adaptation with Marginalized Structured Dropout
نویسندگان
چکیده
[1] John Blitzer et al. Domain Adaptation with Structural Correspondence Learning. In EMNLP’06. [2] Xavier Glorot et al. Domain Adaptation for Large-Scale Sentiment ClassiïňĄcation: A Deep Learning Approach. In ICML ’11 [3] Minmin Chen et al. Marginalized Denoising Autoencoders for Domain Adaptation. In ICML ’12 ACKNOWLEDGMENTS This research was supported by National Science Foundation award 1349837. The first author was also supported by National Science Foundation ACL travel award. EVALUATION: SAME ACCURACY, 25X FASTER!
منابع مشابه
Deep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملA Hassle-Free Unsupervised Domain Adaptation Method Using Instance Similarity Features
We present a simple yet effective unsupervised domain adaptation method that can be generally applied for different NLP tasks. Our method uses unlabeled target domain instances to induce a set of instance similarity features. These features are then combined with the original features to represent labeled source domain instances. Using three NLP tasks, we show that our method consistently outpe...
متن کاملAn Extended Framework for Marginalized Domain Adaptation
We propose an extended framework for marginalized domain adaptation, aimed at addressing unsupervised, supervised and semisupervised scenarios. We argue that the denoising principle should be extended to explicitly promote domain-invariant features as well as help the classification task. Therefore we propose to jointly learn the data auto-encoders and the target classifiers. First, in order to...
متن کاملAdversarial Dropout Regularization
We present a method for transferring neural representations from label-rich source domains to unlabeled target domains. Recent adversarial methods proposed for this task learn to align features across domains by fooling a special domain critic network. However, a drawback of this approach is that the critic simply labels the generated features as in-domain or not, without considering the bounda...
متن کاملDeep Nonlinear Feature Coding for Unsupervised Domain Adaptation
Deep feature learning has recently emerged with demonstrated effectiveness in domain adaptation. In this paper, we propose a Deep Nonlinear Feature Coding framework (DNFC) for unsupervised domain adaptation. DNFC builds on the marginalized stacked denoising autoencoder (mSDA) to extract rich deep features. We introduce two new elements to mSDA: domain divergence minimization by Maximum Mean Dis...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014