Abstract
Existing studies tend to extract the sentiment elements in a generative manner in order to avoid complex modeling. Despite their effectiveness, they ignore importance of the relationships between sentiment elements that could be crucial, making the large pre-trained generative models sub-optimal for modeling sentiment knowledge. Therefore, we introduce two pre-training paradigms to improve the generation model by exploring graph pre-training that targeting to strengthen the model in capturing the elements’ relationships. Specifically, We first employ an Element-level Graph Pre-training paradigm, which is designed to improve the structure awareness of the generative model. Then, we design a Task Decomposition Pre-training paradigm to make the generative model generalizable and robust against various irregular sentiment quadruples. Extensive experiments show the superiority of our proposed method, validate the correctness of our motivation.- Anthology ID:
- 2023.findings-emnlp.234
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3623–3634
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.234
- DOI:
- 10.18653/v1/2023.findings-emnlp.234
- Cite (ACL):
- Xiaoyi Bao, Zhongqing Wang, and Guodong Zhou. 2023. Exploring Graph Pre-training for Aspect-based Sentiment Analysis. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3623–3634, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Exploring Graph Pre-training for Aspect-based Sentiment Analysis (Bao et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2023.findings-emnlp.234.pdf