A Multi-Task Incremental Learning Framework with Category Name Embedding for Aspect-Category Sentiment Analysis
This addresses incremental learning challenges in sentiment analysis for real-world applications, though it is incremental as it builds on multi-task learning methods.
The paper tackled the problem of catastrophic forgetting in incremental learning for aspect-category sentiment analysis by proposing a Category Name Embedding network, achieving state-of-the-art performance on benchmark datasets and a new incremental learning dataset.
(T)ACSA tasks, including aspect-category sentiment analysis (ACSA) and targeted aspect-category sentiment analysis (TACSA), aims at identifying sentiment polarity on predefined categories. Incremental learning on new categories is necessary for (T)ACSA real applications. Though current multi-task learning models achieve good performance in (T)ACSA tasks, they suffer from catastrophic forgetting problems in (T)ACSA incremental learning tasks. In this paper, to make multi-task learning feasible for incremental learning, we proposed Category Name Embedding network (CNE-net). We set both encoder and decoder shared among all categories to weaken the catastrophic forgetting problem. Besides the origin input sentence, we applied another input feature, i.e., category name, for task discrimination. Our model achieved state-of-the-art on two (T)ACSA benchmark datasets. Furthermore, we proposed a dataset for (T)ACSA incremental learning and achieved the best performance compared with other strong baselines.