UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912038874251264 |
|---|---|
| author | Choi, Juhwan Kim, Yeonghwa Yu, Seunguk Yun, JungMin Kim, YoungBin |
| author_facet | Choi, Juhwan Kim, Yeonghwa Yu, Seunguk Yun, JungMin Kim, YoungBin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_01022 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation Choi, Juhwan Kim, Yeonghwa Yu, Seunguk Yun, JungMin Kim, YoungBin Computation and Language Artificial Intelligence 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. |
| title | UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2405.01022 |