Making Flexible Use of Subtasks: A Multiplex Interaction Network for Unified Aspect-based Sentiment Analysis

Aspect Term Extraction (ATE), Opinion Term Extraction (OTE) and Aspect Sentiment Classification (ASC) are the essential building blocks of Aspect-based Sentiment Analysis (ABSA). They are typically treated as separate tasks and are individually studied by previous work. Recent studies intend to incorporate multiple sub-tasks into a unified framework, but suffer from the following major disadvantages: (1) ABSA models are extremely fragile when some sub-tasks are absent; (2) the interactive relations among subtasks are not adequate. To this end, we propose a multi-task learning approach named MIN (Multiplex Interaction Network) to make flexible use of sub-tasks for a unified ABSA. We divide the sub-tasks of ABSA into extractive sub-tasks and classification sub-tasks, and optimize these sub-tasks in a unified manner with multiplex interaction mechanisms. Specifically, we devise a pairwise attention to exploit bidirectional interactions between any arbitrary pair of extractive sub-tasks and a consistency-weighting to perform unidirectional interaction from an extractive sub-task to a classification sub-task. Since the proposed interaction mechanisms are task-agnostic, our model can also work well when some specific sub-tasks are absent. Extensive experiments on two widely used benchmarks with different numbers of sub-tasks demonstrate the superiority of the proposed model.