End-to-End Adversarial Memory Network for Cross-domain Sentiment Classification

By Zheng Li, Yu Zhang, Ying Wei, Yuxiang Wu, Qiang Yang. 2017

256 citations recorded by the source corpus.

Domain adaptation tasks such as cross-domain sentiment classification have raised much attention in recent years. Due to the domain discrepancy, a sentiment classifier trained in a source domain may not work well when directly applied to a target domain. Traditional methods need to manually select pivots, which behave in the same way for discriminative learning in both domains. Recently, deep learning methods have been proposed to learn a representation shared by domains. However, they lack the interpretability to directly identify the pivots. To address the problem, we introduce an end-to-end Adversarial Memory Network (AMN) for cross-domain sentiment classification. Unlike existing methods, the proposed AMN can automatically capture the pivots using an attention mechanism. Our framework consists of two parameter-shared memory networks with one for sentiment classification and the other for domain classification. The two networks are jointly trained so that the selected features minimize the sentiment classification error and at the same time make the domain classifier indiscriminative between the representations from the source or target domains. Moreover, unlike deep learning methods that cannot tell which words are the pivots, AMN can offer a direct visualization of them. Experiments on the Amazon review dataset demonstrate that AMN can significantly outperform state-of-the-art methods.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

1. Xing Xie
2. Guodong Long
3. Jing Jiang
4. Chengqi Zhang
5. Hongwei Wang
6. Wenjie Li
7. Miao Zhao
8. Tianyi Zhou

In Computer Vision and Pattern Recognition

1. Alan Ramponi
2. Jing Jiang
3. Tao Shen
4. Xing Xie
5. Minyi Guo
6. Shuai Wang
7. Tianyi Zhou
8. Antonio Liotta

Citations in the corpus

• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, background): “rations on the external memory enable memory networks to extract long-distance dependency in texts. Researchers have also proposed using memory networks in other tasks such as sentiment classification[12]andrecommendation[5,8].Notethattheseworks usually focus on entry-level or sentence-level memorie”
• Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling (2018, methodology): “Li et al. (2017) applies the multi-hop attention mechanism to transfer learning for cross-domain sentiment analysis without any RNN/CNN structure.”
• A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances (2022, background): “Deep RNN learning for TSA.”
• Sentiment Classification by Leveraging the Shared Knowledge from a Sequence of Domains (2019, background): “Transfer learning or domain adaptation uses labeled training examples from the source domain to help learning in the target domain that has no or very few labeled training examples [1,12,18,22,40].”
• Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling (2018, unknown): “, 2016], sentiment classification [Li et al., 2017b], etc.”
• Neural Unsupervised Domain Adaptation in NLP—A Survey (2020, background): “, pivot prediction and sentiment) (Miller, 2019) and learn pivots automatically via attention (Li et al., 2017), similar to work on automatic non-pivot identification (Li et al.”