Low-Resource Comparative Opinion Quintuple Extraction by Data Augmentation with Prompting

Qingting Xu, Yu Hong, Fubang Zhao, Kaisong Song, Yangyang Kang, Jiaxiang Chen, Guodong Zhou


Abstract
Comparative Opinion Quintuple Extraction (COQE) aims to predict comparative opinion quintuples from comparative sentences. These quintuples include subject, object, shareable aspect, comparative opinion, and preference. The existing pipeline-based COQE method fails in error propagation. In addition, the complexity and insufficient amounts of annotated data hinder the performance of COQE models. In this paper, we introduce a novel approach called low-resource comparative opinion quintuple extraction by Data Augmentation with Prompting (DAP). Firstly, we present an end-to-end model architecture better suited to the data augmentation method from triplets to quintuples and can effectively avoid error propagation. Additionally, we introduce a data-centric augmentation approach that leverages the robust generative abilities of ChatGPT and integrates transfer learning techniques. Experimental results over three datasets (Camera, Car, Ele) demonstrate that our approach yields substantial improvements and achieves state-of-the-art results. The source code and data are publicly released at: https://github.com/qtxu-nlp/COQE-DAP.
Anthology ID:
2023.findings-emnlp.255
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:
3892–3897
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.255
DOI:
10.18653/v1/2023.findings-emnlp.255
Bibkey:
Cite (ACL):
Qingting Xu, Yu Hong, Fubang Zhao, Kaisong Song, Yangyang Kang, Jiaxiang Chen, and Guodong Zhou. 2023. Low-Resource Comparative Opinion Quintuple Extraction by Data Augmentation with Prompting. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3892–3897, Singapore. Association for Computational Linguistics.
Cite (Informal):
Low-Resource Comparative Opinion Quintuple Extraction by Data Augmentation with Prompting (Xu et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.255.pdf