Structure-aware Generation Model for Cross-Domain Aspect-based Sentiment Classification

Shichen Li, Zhongqing Wang, Yanzhi Xu, Guodong Zhou


Abstract
Employing pre-trained generation models for cross-domain aspect-based sentiment classification has recently led to large improvements. However, they ignore the importance of syntactic structures, which have shown appealing effectiveness in classification based models. Different from previous studies, efficiently encoding the syntactic structure in generation model is challenging because such models are pretrained on natural language, and modeling structured data may lead to catastrophic forgetting of distributional knowledge. In this study, we propose a novel structure-aware generation model to tackle this challenge. In particular, a prompt-driven strategy is designed to bridge the gap between different domains, by capturing implicit syntactic information from the input and output sides. Furthermore, the syntactic structure is explicitly encoded into the structure-aware generation model, which can effectively learn domain-irrelevant features based on syntactic pivot features. Empirical results demonstrate the effectiveness of the proposed structure-aware generation model over several strong baselines. The results also indicate the proposed model is capable of leveraging the input syntactic structure into the generation model.
Anthology ID:
2024.lrec-main.1335
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:
15373–15383
Language:
URL:
https://aclanthology.org/2024.lrec-main.1335
DOI:
Bibkey:
Cite (ACL):
Shichen Li, Zhongqing Wang, Yanzhi Xu, and Guodong Zhou. 2024. Structure-aware Generation Model for Cross-Domain Aspect-based Sentiment Classification. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15373–15383, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Structure-aware Generation Model for Cross-Domain Aspect-based Sentiment Classification (Li et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.1335.pdf