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.
@article{arxiv.2112.03271,
title = {Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks},
author = {Zixuan Ke and Hu Xu and Bing Liu},
journal= {arXiv preprint arXiv:2112.03271},
year = {2021}
}
Comments
arXiv admin note: text overlap with arXiv:2112.02714, arXiv:2112.02706