Forward and Backward Knowledge Transfer for Sentiment Classification

By Hao Wang, Bing Liu, Shuai Wang, Nianzu Ma, Yan Yang. 2019

18 citations recorded by the source corpus.

This paper studies the problem of learning a sequence of sentiment classification tasks. The learned knowledge from each task is retained and used to help future or subsequent task learning. This learning paradigm is called Lifelong Learning (LL). However, existing LL methods either only transfer knowledge forward to help future learning and do not go back to improve the model of a previous task or require the training data of the previous task to retrain its model to exploit backward/reverse knowledge transfer. This paper studies reverse knowledge transfer of LL in the context of naive Bayesian (NB) classification. It aims to improve the model of a previous task by leveraging future knowledge without retraining using its training data. This is done by exploiting a key characteristic of the generative model of NB. That is, it is possible to improve the NB classifier for a task by improving its model parameters directly by using the retained knowledge from other tasks. Experimental results show that the proposed method markedly outperforms existing LL baselines.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, 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 Artificial Intelligence

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

In Representation & Self-Supervised Learning

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

In Sentiment & Opinion Analysis

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

Citations in the corpus

• Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks (2021, methodology): “Ke et al. (2020) and Wang et al. (2019) also did backward transfer.”
• Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning (2021, methodology): “[6] and [61] proposed two Naive Bayesian methods to help improve the new task learning.”
• Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks (2021, methodology): “A heuristic NB method was also used in (Wang et al., 2019).”
• Continual Learning with Knowledge Transfer for Sentiment Classification (2021, methodology): “The authors of [5, 28] proposed a Naive Bayes (NB) approach to help improve the new task learning.”
• Using the Past Knowledge to Improve Sentiment Classification (2020, methodology): “Although there is some existing work on lifelong sentiment classification (Chen et al., 2015; Wang et al., 2019) based on naive Bayes.”
• BNS: Building Network Structures Dynamically for Continual Learning (2021, methodology): “However, since they use traditional learning methods such as regression [47] and naive Bayes [9, 57] to build an independent model for each task, there is no CF.”