GCNet: Global-and-Context Collaborative Learning for Aspect-Based Sentiment Analysis

Ting Zhou, Ying Shen, Yinghui Li


Abstract
Aspect-Based Sentiment Analysis (ABSA) aims to determine the sentiment polarities of specified aspect terms in a sentence. Most previous approaches mainly use an attention mechanism or graph neural networks based on dependency trees to explicitly model the connections between aspect terms and opinion words. However, these methods may not effectively address cases where the sentiment of an aspect term is implicitly described, as the corresponding opinion words may not directly appear in the sentence. To alleviate this issue, in this paper, we propose a GCNet that explicitly leverages global semantic information to guide context encoding. Particularly, we design a semantics encoding module that incorporates global semantic features into sequential modeling process to enable the consideration of the overall sentiment tendency of a sentence, while the global semantic features are also refined by adaptively focusing on different parts of the sentence. Moreover, for a comprehensive sentence analysis, we also include a syntactic feature encoding module along with a pre-fusion module to integrate the refined global features with the syntactic representations. Extensive experiments on three public datasets demonstrate that our model outperforms state-of-the-art methods, indicating the robustness and effectiveness of our approach.
Anthology ID:
2024.lrec-main.669
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
7570–7580
Language:
URL:
https://aclanthology.org/2024.lrec-main.669
DOI:
Bibkey:
Cite (ACL):
Ting Zhou, Ying Shen, and Yinghui Li. 2024. GCNet: Global-and-Context Collaborative Learning for Aspect-Based Sentiment Analysis. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7570–7580, Torino, Italia. ELRA and ICCL.
Cite (Informal):
GCNet: Global-and-Context Collaborative Learning for Aspect-Based Sentiment Analysis (Zhou et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.669.pdf