Author(s)

Hao Zhang¹, Yegang Li¹, Jiachen Yang¹, Rujiang Bai²

¹School of Computer Science and Technology, Shandong University of Technology, Zibo, China.
²Institute of Information Management, Shandong University of Technology, Zibo, China.

To address the difficulty of training high-quality models in some specific domains due to the lack of fine-grained annotation resources, we propose in this paper a knowledge-integrated cross-domain data generation method for unsupervised domain adaptation tasks. Specifically, we extract domain features, lexical and syntactic knowledge from source-domain and target-domain data, and use a masking model with an extended masking strategy and a re-masking strategy to obtain domain-specific data that remove domain-specific features. Finally, we improve the sequence generation model BART and use it to generate high-quality target domain data for the task of aspect and opinion co-extraction from the target domain. Experiments were performed on three conventional English datasets from different domains, and our method generates more accurate and diverse target domain data with the best results compared to previous methods.

Knowledge-Integrate, Domain Adaptation, Text Generation, Aspect and Opinion Co-Extraction

Zhang, H. , Li, Y. , Yang, J. and Bai, R. (2023) A Knowledge-Integrate Cross-Domain Data Generation Method for Aspect and Opinion Co-Extraction. Journal of Computer and Communications, 11, 31-48. doi: 10.4236/jcc.2023.1112003.