Adapting Bert For Continual Learning Of A Sequence Of Aspect Sentiment Classification Tasks

# Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks

**arXiv ID:** 2112.03271
**Authors:** Zixuan Ke, Hu Xu, Bing Liu
**Published:** 2021-12-06T02:46:06Z
**Abstract:**
This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks. Although some CL techniques have been proposed for document sentiment classification, we are not aware of any CL work on ASC. A CL system that incrementally learns a sequence of ASC tasks should address the following two issues: (1) transfer knowledge learned from previous tasks to the new task to help it learn a better model, and (2) maintain the performance of the models for previous tasks so that they are not forgotten. This paper proposes a novel capsule network based model called B-CL to address these issues. B-CL markedly improves the ASC performance on both the new task and the old tasks via forward and backward knowledge transfer. The effectiveness of B-CL is demonstrated through extensive experiments.

## Skill Description

This skill is generated from the arXiv paper: Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks (2112.03271).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2112.03271](http://arxiv.org/abs/2112.03271v1)