Block-level dependency syntax based model for end-to-end aspect-based sentiment analysis

Abstract

End-to-End aspect-based sentiment analysis (E2E-ABSA) aims to jointly extract aspect terms and identify their sentiment polarities. Although previous research has demonstrated that syntax knowledge can be beneficial for E2E-ABSA, standard syntax dependency parsing struggles to capture the block-level relation between aspect and opinion terms, which hinders the role of syntax in E2E-ABSA. To address this issue, this paper proposes a block-level dependency syntax parsing (BDEP) based model to enhance the performance of E2E-ABSA. BDEP is constructed by incorporating routine dependency syntax parsing and part-of-speech tagging, which enables the capture of block-level relations. Subsequently. the BDEP-guided interactive attention module (BDEP-IAM) is used to obtain the aspect-aware representation of each word. Finally the adaptive fusion module is leveraged to combine the semantic-syntactic representation to simultaneously extract the aspect term and identify aspect-orient sentiment polarity. The model is evaluated on five benchmark datasets, including Laptop14, Rest _ALL, Restaurant14, Restaurant15, and TWITTER, with F1 scores of 62.67%, 76.53%, 75.42%, 62.21%, and 58.03%, respectively. The results show that our model outperforms the other compared state-of-the-art (SOTA) methods on all datasets. Additionally, ablation experiments confirm the efficacy of BDEP and IAM in improving aspect-level sentiment analysis.

Keywords: Adaptive semantic-syntactic fusion; Aspect term; Aspect-based sentiment analysis; Block-dependency syntax-guided interactive attention; Block-level dependency syntax.