Sentiment Classification by Leveraging the Shared Knowledge from a Sequence of Domains

By Guangyi Lv, Shuai Wang, Bing Liu, Enhong Chen, Kun Zhang. 2019

44 citations recorded by the source corpus.

Subfields: Natural Language Processing, Sentiment & Opinion Analysis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Bing Liu
2. Hu Xu
3. Lei Shu
4. Zixuan Ke
5. Shuai Wang
6. Wenpeng Hu
7. Qi Qin
8. Nianzu Ma

In Sentiment & Opinion Analysis

1. Bing Liu
2. Zixuan Ke
3. Hu Xu
4. Lei Shu
5. Qi Qin
6. Nianzu Ma
7. Wenpeng Hu
8. Shuai Wang

Citations in the corpus

• Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning (2021, methodology): “However, all these works do not deal with CF. SRK [37] and KAN [22] try to deal with both CF and knowledge transfer in continual sentiment classification.”
• Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks (2021, methodology): “KAN (Ke et al., 2020b) and SRK (Lv et al., 2019) are TIL methods for document sentiment classification.”
• Continual Learning by Using Information of Each Class Holistically (2021, methodology): “There is also a less frequently used CL setting (Lv et al. 2019; van de Ven and Tolias 2019), which is like TCL but the task-id is not provided during testing.”
• Learning on the Job: Online Lifelong and Continual Learning (2020, methodology): “Lv et al. (2019) proposed a method, called SRK, which deals with CF and also improves the accuracy of the new task learning significantly.”
• CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks (2021, methodology): “Existing CL systems SRK (Lv et al., 2019) and KAN (Ke et al.”
• Forward and Backward Knowledge Transfer for Sentiment Classification (2019, methodology): “Regarding the deep learning baseline Lv et al. (2019), we ran it on a GPU server with Python as its original system used Python.”
• Continual learning in recurrent neural networks (2020, methodology): “Specifically, EWC first applies a Laplace approximation MacKay (1992) (using the MAP solution ψ̃(K−1) obtained at the end of training of task K − 1) to obtain a Gaussian q ζ (ψ) with mean ψ̃ (K−1) and precision matrix F = ∑K−1 k=1 F , where F (k) denotes the empirical Fisher matrix.”
• Using the Past Knowledge to Improve Sentiment Classification (2020, methodology): “Lv et al. (2019) proposed a model using two networks, one for knowledge retention and one for feature learning.”