Bayes-enhanced Lifelong Attention Networks for Sentiment Classification
Hao Wang, Shuai Wang, Sahisnu Mazumder, Bing Liu, Yan Yang, Tianrui Li
Abstract
The classic deep learning paradigm learns a model from the training data of a single task and the learned model is also tested on the same task. This paper studies the problem of learning a sequence of tasks (sentiment classification tasks in our case). After each sentiment classification task is learned, its knowledge is retained to help future task learning. Following this setting, we explore attention neural networks and propose a Bayes-enhanced Lifelong Attention Network (BLAN). The key idea is to exploit the generative parameters of naive Bayes to learn attention knowledge. The learned knowledge from each task is stored in a knowledge base and later used to build lifelong attentions. The constructed lifelong attentions are then used to enhance the attention of the network to help new task learning. Experimental results on product reviews from Amazon.com show the effectiveness of the proposed model.- Anthology ID:
- 2020.coling-main.50
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Editors:
- Donia Scott, Nuria Bel, Chengqing Zong
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 580–591
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.50
- DOI:
- 10.18653/v1/2020.coling-main.50
- Cite (ACL):
- Hao Wang, Shuai Wang, Sahisnu Mazumder, Bing Liu, Yan Yang, and Tianrui Li. 2020. Bayes-enhanced Lifelong Attention Networks for Sentiment Classification. In Proceedings of the 28th International Conference on Computational Linguistics, pages 580–591, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- Bayes-enhanced Lifelong Attention Networks for Sentiment Classification (Wang et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.50.pdf