Enhancement of Target-Oriented Opinion Words Extraction with Multiview-Trained Machine Reading Comprehension Model

• Published in: Computational intelligence and neuroscience 2021, Vol.2021 (1), p.6645871-6645871
• Main Authors: Zhang, Jingyuan, Zhang, Zequn, Guo, Zhi, Jin, Li, Liu, Kang, Liu, Qing
• Format: Article
• Language: English
• Subjects: Annotations; Data mining; Knowledge; Neural networks; Operating systems; Position indicators; Product reviews; Questions; Reading comprehension; Representations; Semantics; Sentiment analysis; User interface
• ISSN: 1687-5265; 1687-5273
• DOI: 10.1155/2021/6645871

Target-oriented opinion words extraction (TOWE) seeks to identify opinion expressions oriented to a specific target, and it is a crucial step toward fine-grained opinion mining. Recent neural networks have achieved significant success in this task by building target-aware representations. However, there are still two limitations of these methods that hinder the progress of TOWE. Mainstream approaches typically utilize position indicators to mark the given target, which is a naive strategy and lacks task-specific semantic meaning. Meanwhile, the annotated target-opinion pairs contain rich latent structural knowledge from multiple perspectives, but existing methods only exploit the TOWE view. To tackle these issues, we formulate the TOWE task as a question answering (QA) problem and leverage a machine reading comprehension (MRC) model trained with a multiview paradigm to extract targeted opinions. Specifically, we introduce a template-based pseudo-question generation method and utilize deep attention interaction to build target-aware context representations and extract related opinion words. To take advantage of latent structural correlations, we further cast the opinion-target structure into three distinct yet correlated views and leverage meta-learning to aggregate common knowledge among them to enhance the TOWE task. We evaluate the proposed model on four benchmark datasets, and our method achieves new state-of-the-art results. Extensional experiments have shown that the pipeline method with our approach could surpass existing opinion pair extraction models, including joint methods that are usually believed to work better.