A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis

Abstract

Aspect based sentiment analysis (ABSA) involves three fundamental subtasks: aspect term extraction, opinion term extraction, and aspect-level sentiment classification. Early works only focused on solving one of these subtasks individually. Some recent work focused on solving a combination of two subtasks, e.g., extracting aspect terms along with sentiment polarities or extracting the aspect and opinion terms pair-wisely. More recently, the triple extraction task has been proposed, i.e., extracting the (aspect term, opinion term, sentiment polarity) triples from a sentence. However, previous approaches fail to solve all subtasks in a unified end-to-end framework. In this paper, we propose a complete solution for ABSA. We construct two machine reading comprehension (MRC) problems and solve all subtasks by joint training two BERT-MRC models with parameters sharing. We conduct experiments on these subtasks, and results on several benchmark datasets demonstrate the effectiveness of our proposed framework, which significantly outperforms existing state-of-the-art methods.

to appear in AAAI2021

References in corpus (1)

• Learning Recurrent Span Representations for Extractive Question Answering

Cited by in corpus (8)

• Paradigm Shift in Natural Language Processing
• Deep Context- and Relation-Aware Learning for Aspect-based Sentiment Analysis
• A Unified Generative Framework for Aspect-Based Sentiment Analysis
• Explicit Interaction Network for Aspect Sentiment Triplet Extraction
• Aspect Sentiment Quad Prediction as Paraphrase Generation
• Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction
• Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Model
• Human-in-the-Loop Disinformation Detection: Stance, Sentiment, or Something Else?