CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks

By Zixuan Ke, Bing Liu, Hu Xu, Lei Shu. 2021

68 citations recorded by the source corpus.

This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks in a particular CL setting called domain incremental learning (DIL). Each task is from a different domain or product. The DIL setting is particularly suited to ASC because in testing the system needs not know the task/domain to which the test data belongs. To our knowledge, this setting has not been studied before for ASC. This paper proposes a novel model called CLASSIC. The key novelty is a contrastive continual learning method that enables both knowledge transfer across tasks and knowledge distillation from old tasks to the new task, which eliminates the need for task ids in testing. Experimental results show the high effectiveness of CLASSIC.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Sentiment & Opinion Analysis, Meta & Continual Learning

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. Bing Liu
2. Zixuan Ke
3. Hu Xu
4. Lei Shu
5. B. Liu
6. Bin Liu
7. Gyuhak Kim
8. Nianzu Ma

In Computer Vision and Pattern Recognition

1. Zixuan Ke
2. Bin Liu
3. Bing Liu
4. Hu Xu
5. Gyuhak Kim
6. Dongyan Zhao
7. Lei Shu
8. Yiduo Guo

In Sentiment & Opinion Analysis

1. Bing Liu
2. Zixuan Ke
3. Hu Xu
4. Lei Shu
5. Nianzu Ma
6. Bin Liu
7. B. Liu
8. Dongyan Zhao

In Meta & Continual Learning

1. Bing Liu
2. Zixuan Ke
3. Bin Liu
4. Gyuhak Kim
5. Hu Xu
6. Lei Shu
7. Tatsuya Konishi
8. B. Liu

Citations in the corpus

• Continual Training of Language Models for Few-Shot Learning (2022, background): “…(Liu et al., 2019a), translation (Khayral-lah et al., 2018), cross-lingual modeling (Liu et al., 2020b), question answering (Greco et al., 2019) and text classification (Ke et al., 2021a,b; Sun et al., 2020; Huang et al., 2021; Chuang et al., 2020; Mehta et al., 2021; Madotto et al., 2020).”
• Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection (2022, background): “However, when moving to lifelong learning setting, their performance significantly drops (Kirkpatrick et al., 2017; Aljundi et al., 2019; Biesialska et al., 2020; Cui et al., 2021; Ke et al., 2021b; Madotto et al., 2021; Ke et al., 2021a; Feng et al., 2022).”
• Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning (2021, methodology): “CLASSIC [23] is another recent work on continual learning for knowledge transfer, but its CL setting is domain continual learning.”
• Continual Pre-training of Language Models (2023, methodology): “Those baselines (BCL, CLASSIC and DEMIX) perform knowledge transfer achieve better results but still poorer than DAS.”
• Online Continual Learning through Mutual Information Maximization (2022, background): “See (Ke et al., 2021; van de Ven & Tolias, 2019) for task incremental learning and domain incremental learning settings.”
• Continual Few-shot Intent Detection (2022, background): “However, there are two issues: (i) over-parameterization of PrLMs makes them prone to overfit the current task and cause catastrophic forgetting of previous knowledge (Ke et al., 2021a; Yuan et al., 2021).”
• Three types of incremental learning (2022, unknown): “16,17 ).”