UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation

• DOI: 10.48550/arxiv.2405.01022
• Publication Date: 2024-01-01
• Authors: Choi, Juhwan; Kim, Yeonghwa; Yu, Seunguk; Yun, JungMin; Kim, YoungBin
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; Computation and Language (cs.CL)

Although pre-trained language models have exhibited great flexibility and versatility with prompt-based few-shot learning, they suffer from the extensive parameter size and limited applicability for inference. Recent studies have suggested that PLMs be used as dataset generators and a tiny task-specific model be trained to achieve efficient inference. However, their applicability to various domains is limited because they tend to generate domain-specific datasets. In this work, we propose a novel approach to universal domain generalization that generates a dataset regardless of the target domain. This allows for generalization of the tiny task model to any domain that shares the label space, thus enhancing the real-world applicability of the dataset generation paradigm. Our experiments indicate that the proposed method accomplishes generalizability across various domains while using a parameter set that is orders of magnitude smaller than PLMs.<br/>EMNLP 2024: Camera-ready version<br/>