Learnable Dependency-based Double Graph Structure for Aspect-based Sentiment Analysis

Yinglong Ma, Yunhe Pang


Abstract
Dependency tree-based methods might be susceptible to the dependency tree due to that they inevitably introduce noisy information and neglect the rich relation information between words. In this paper, we propose a learnable dependency-based double graph (LD2G) model for aspect-based sentiment classification. We use multi-task learning for domain adaptive pretraining, which combines Biaffine Attention and Mask Language Model by incorporating features such as structure, relations and linguistic features in the sentiment text. Then we utilize the dependency enhanced double graph-based MPNN to deeply fuse structure features and relation features that are affected with each other for ASC. Experiment on four benchmark datasets shows that our model is superior to the state-of-the-art approaches.
Anthology ID:
2022.coling-1.618
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
7086–7092
Language:
URL:
https://aclanthology.org/2022.coling-1.618
DOI:
Bibkey:
Cite (ACL):
Yinglong Ma and Yunhe Pang. 2022. Learnable Dependency-based Double Graph Structure for Aspect-based Sentiment Analysis. In Proceedings of the 29th International Conference on Computational Linguistics, pages 7086–7092, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Learnable Dependency-based Double Graph Structure for Aspect-based Sentiment Analysis (Ma & Pang, COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.618.pdf