论文标题
一个多任务增量学习框架，具有类别名称嵌入用于方面类别情感分析的类别名称
A Multi-Task Incremental Learning Framework with Category Name Embedding for Aspect-Category Sentiment Analysis
论文作者
论文摘要
（T）ACSA任务，包括方面类别情感分析（ACSA）和有针对性的方面类别情感分析（TACSA），旨在识别预定义类别的情感极性。对于（t）ACSA真实应用，需要增量的新类别学习。尽管当前的多任务学习模型在（T）ACSA任务中实现了良好的性能，但它们却遭受了灾难性的遗忘（T）ACSA增量学习任务中的问题。在本文中，为了使多任务学习可用于增量学习，我们提出了类别名称嵌入网络（CNE-net）。我们将编码器和解码器都在所有类别之间共享，以削弱灾难性的遗忘问题。除了原点输入句子外，我们还应用了另一个输入功能，即类别名称，以进行任务歧视。我们的模型在两个（t）ACSA基准数据集上实现了最先进的功能。此外，我们提出了一个用于（T）ACSA增量学习的数据集，并与其他强基础相比，取得了最佳性能。
(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.
