Bi-Transferring Deep Neural Networks for Domain Adaptation
By Guangyou Zhou, Zhiwen Xie, Xiangji Huang, Tingting He. 2016
48 citations recorded by the source corpus.
Sentiment classification aims to automatically predict sentiment polarity (e.g., positive or negative) of user generated sentiment data (e.g., reviews, blogs). Due to the mismatch among different domains, a sentiment classifier trained in one domain may not work well when directly applied to other domains. Thus, domain adaptation for sentiment classification algorithms are highly desirable to reduce the domain discrepancy and manual labeling costs. To address the above challenge, we propose a novel domain adaptation method, called Bi-Transferring Deep Neural Networks (BTDNNs). The proposed BTDNNs attempts to transfer the source domain examples to the target domain, and also transfer the target domain examples to the source domain. The linear transformation of BTDNNs ensures the feasibility of transferring between domains, and the distribution consistency between the transferred domain and the desirable domain is constrained with a linear data reconstruction manner. As a result, the transferred source domain is supervised and follows similar distribution as the target domain. Therefore, any supervised method can be used on the transferred source domain to train a classifier for sentiment classification in a target domain. We conduct experiments on a benchmark composed of reviews of 4 types of Amazon products. Experimental results show that our proposed approach significantly outperforms the several baseline methods, and achieves an accuracy which is competitive with the state-of-the-art method for domain adaptation.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sebastian Ruder
- Shiyu Chang
- Mo Yu
- Barbara Plank
- Mohit Bansal
- Regina Barzilay
- Yoav Goldberg
- Luke S. Zettlemoyer
Citations in the corpus
- Knowledge Adaptation: Teaching to Adapt (2017, methodology): “Finally, Zhou et al. (2016) transferred the source examples to the target domain and vice versa using BiTransferring Deep Neural Networks, while Bousmalis et al. (2016) propose Domain Separation Networks.”
- Deriving Machine Attention from Human Rationales (2018, background): “Existing meth-ods commonly adapt the classifier by aligning the representations between the source and target domains (Glorot et al., 2011; Chen et al., 2012; Zhou et al., 2016; Ganin et al., 2016; Zhang et al., 2017).”
- Strong Baselines for Neural Semi-Supervised Learning under Domain Shift (2018, background): “, 2017) or on a single benchmark (Zhou et al., 2016), which carries the risk of overfitting to the task.”