Abstract
Recently, aspect sentiment quad prediction (ASQP) has become a popular task in the field of aspect-level sentiment analysis. Previous work utilizes a predefined template to paraphrase the original sentence into a structure target sequence, which can be easily decoded as quadruplets of the form (aspect category, aspect term, opinion term, sentiment polarity). The template involves the four elements in a fixed order. However, we observe that this solution contradicts with the order-free property of the ASQP task, since there is no need to fix the template order as long as the quadruplet is extracted correctly. Inspired by the observation, we study the effects of template orders and find that some orders help the generative model achieve better performance. It is hypothesized that different orders provide various views of the quadruplet. Therefore, we propose a simple but effective method to identify the most proper orders, and further combine multiple proper templates as data augmentation to improve the ASQP task. Specifically, we use the pre-trained language model to select the orders with minimal entropy. By fine-tuning the pre-trained language model with these template orders, our approach improves the performance of quad prediction, and outperforms state-of-the-art methods significantly in low-resource settings.- Anthology ID:
- 2022.emnlp-main.538
- 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:
- 7889–7900
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.538
- DOI:
- 10.18653/v1/2022.emnlp-main.538
- Cite (ACL):
- Mengting Hu, Yike Wu, Hang Gao, Yinhao Bai, and Shiwan Zhao. 2022. Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7889–7900, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation (Hu et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.emnlp-main.538.pdf