Affective Knowledge Enhanced Multiple-Graph Fusion Networks for Aspect-based Sentiment Analysis

Siyu Tang, Heyan Chai, Ziyi Yao, Ye Ding, Cuiyun Gao, Binxing Fang, Qing Liao


Abstract
Aspect-based sentiment analysis aims to identify sentiment polarity of social media users toward different aspects. Most recent methods adopt the aspect-centric latent tree to connect aspects and their corresponding opinion words, thinking that would facilitate establishing the relationship between aspects and opinion words.However, these methods ignore the roles of syntax dependency relation labels and affective semantic information in determining the sentiment polarity, resulting in the wrong prediction.In this paper, we propose a novel multi-graph fusion network (MGFN) based on latent graph to leverage the richer syntax dependency relation label information and affective semantic information of words.Specifically, we construct a novel syntax-aware latent graph (SaLG) to fully leverage the syntax dependency relation label information to facilitate the learning of sentiment representations. Subsequently, a multi-graph fusion module is proposed to fuse semantic information of surrounding contexts of aspects adaptively. Furthermore, we design an affective refinement strategy to guide the MGFN to capture significant affective clues. Extensive experiments on three datasets demonstrate that our MGFN model outperforms all state-of-the-art methods and verify the effectiveness of our model.
Anthology ID:
2022.emnlp-main.359
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5352–5362
Language:
URL:
https://aclanthology.org/2022.emnlp-main.359
DOI:
10.18653/v1/2022.emnlp-main.359
Bibkey:
Cite (ACL):
Siyu Tang, Heyan Chai, Ziyi Yao, Ye Ding, Cuiyun Gao, Binxing Fang, and Qing Liao. 2022. Affective Knowledge Enhanced Multiple-Graph Fusion Networks for Aspect-based Sentiment Analysis. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5352–5362, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Affective Knowledge Enhanced Multiple-Graph Fusion Networks for Aspect-based Sentiment Analysis (Tang et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.359.pdf