Frustratingly Easy Domain Adaptation
نویسنده
چکیده
We describe an approach to domain adaptation that is appropriate exactly in the case when one has enough “target” data to do slightly better than just using only “source” data. Our approach is incredibly simple, easy to implement as a preprocessing step (10 lines of Perl!) and outperforms stateof-the-art approaches on a range of datasets. Moreover, it is trivially extended to a multidomain adaptation problem, where one has data from a variety of different domains.
منابع مشابه
Return of Frustratingly Easy Domain Adaptation
Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of conventional machine learning methods. Supervised domain adaptation methods have been proposed for the case when the target data have labels, including some that perform very w...
متن کاملDeep CORAL: Correlation Alignment for Deep Domain Adaptation
Deep neural networks are able to learn powerful representations from large quantities of labeled input data, however they cannot always generalize well across changes in input distributions. Domain adaptation algorithms have been proposed to compensate for the degradation in performance due to domain shift. In this paper, we address the case when the target domain is unlabeled, requiring unsupe...
متن کاملFrustratingly Easy Semi-Supervised Domain Adaptation
In this work, we propose a semisupervised extension to a well-known supervised domain adaptation approach (EA) (Daumé III, 2007). Our proposed approach (EA++) builds on the notion of augmented space (introduced in EA) and harnesses unlabeled data in target domain to ameliorate the transfer of information from source to target. This semisupervised approach to domain adaptation is extremely simpl...
متن کاملFrustratingly Easy Neural Domain Adaptation
Popular techniques for domain adaptation such as the feature augmentation method of Daumé III (2009) have mostly been considered for sparse binary-valued features, but not for dense realvalued features such as those used in neural networks. In this paper, we describe simple neural extensions of these techniques. First, we propose a natural generalization of the feature augmentation method that ...
متن کاملFrustratingly Hard Domain Adaptation for Dependency Parsing
We describe some challenges of adaptation in the 2007 CoNLL Shared Task on Domain Adaptation. Our error analysis for this task suggests that a primary source of error is differences in annotation guidelines between treebanks. Our suspicions are supported by the observation that no team was able to improve target domain performance substantially over a state of the art baseline.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/0907.1815 شماره
صفحات -
تاریخ انتشار 2007