SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916331674140672 |
|---|---|
| author | Jin, Chunzhen Huang, Yongfeng Wang, Yaqi Cao, Peng Zaiane, Osmar |
| author_facet | Jin, Chunzhen Huang, Yongfeng Wang, Yaqi Cao, Peng Zaiane, Osmar |
| contents | Text style transfer, an important research direction in natural language processing, aims to adapt the text to various preferences but often faces challenges with limited resources. In this work, we introduce a novel method termed Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning (SETTP) for effective style transfer in low-resource scenarios. First, SETTP learns source style-level prompts containing fundamental style characteristics from high-resource style transfer. During training, the source style-level prompts are transferred through an attention module to derive a target style-level prompt for beneficial knowledge provision in low-resource style transfer. Additionally, we propose instance-level prompts obtained by clustering the target resources based on the semantic content to reduce semantic bias. We also propose an automated evaluation approach of style similarity based on alignment with human evaluations using ChatGPT-4. Our experiments across three resourceful styles show that SETTP requires only 1/20th of the data volume to achieve performance comparable to state-of-the-art methods. In tasks involving scarce data like writing style and role style, SETTP outperforms previous methods by 16.24\%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15556 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning Jin, Chunzhen Huang, Yongfeng Wang, Yaqi Cao, Peng Zaiane, Osmar Computation and Language Text style transfer, an important research direction in natural language processing, aims to adapt the text to various preferences but often faces challenges with limited resources. In this work, we introduce a novel method termed Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning (SETTP) for effective style transfer in low-resource scenarios. First, SETTP learns source style-level prompts containing fundamental style characteristics from high-resource style transfer. During training, the source style-level prompts are transferred through an attention module to derive a target style-level prompt for beneficial knowledge provision in low-resource style transfer. Additionally, we propose instance-level prompts obtained by clustering the target resources based on the semantic content to reduce semantic bias. We also propose an automated evaluation approach of style similarity based on alignment with human evaluations using ChatGPT-4. Our experiments across three resourceful styles show that SETTP requires only 1/20th of the data volume to achieve performance comparable to state-of-the-art methods. In tasks involving scarce data like writing style and role style, SETTP outperforms previous methods by 16.24\%. |
| title | SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.15556 |