Aspect category detection (ACD) in sentiment analysis aims to identify the aspect categories mentioned in a sentence. In this paper, we formulate ACD in the few-shot learning scenario. However, existing few-shot learning approaches mainly focus on single-label predictions. These methods can not work well for the ACD task since a sentence may contain multiple aspect categories. Therefore, we propose a multi-label few-shot learning method based on the prototypical network. To alleviate the noise, we design two effective attention mechanisms. The support-set attention aims to extract better prototypes by removing irrelevant aspects. The query-set attention computes multiple prototype-specific representations for each query instance, which are then used to compute accurate distances with the corresponding prototypes. To achieve multi-label inference, we further learn a dynamic threshold per instance by a policy network. Extensive experimental results on three datasets demonstrate that the proposed method significantly outperforms strong baselines.
翻译:情绪分析中的显示类别检测(ACD)旨在确定句子中提及的方面类别。在本文中,我们在微小的学习情景中制定ACD。然而,现有的微小的学习方法主要侧重于单标签预测。这些方法对 ACD 任务无法很好地发挥作用,因为一个句子可能包含多个方面类别。因此,我们建议基于原型网络的多标签微小的学习方法。为了缓解噪音,我们设计了两种有效的关注机制。支持设置的注意旨在通过删除无关的方面来提取更好的原型。查询设置的注意为每个查询实例计算多个原型的表示,然后用来计算与相应原型的准确距离。为了实现多标签推断,我们通过政策网络进一步学习了每个实例的动态阈值。关于三个数据集的广泛实验结果表明,拟议的方法大大超越了强的基线。