Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2508.08651 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912532990525440 |
|---|---|
| author | Šmíd, Jakub Přibáň, Pavel |
| author_facet | Šmíd, Jakub Přibáň, Pavel |
| contents | This paper introduces the first prompt-based methods for aspect-based sentiment analysis and sentiment classification in Czech. We employ the sequence-to-sequence models to solve the aspect-based tasks simultaneously and demonstrate the superiority of our prompt-based approach over traditional fine-tuning. In addition, we conduct zero-shot and few-shot learning experiments for sentiment classification and show that prompting yields significantly better results with limited training examples compared to traditional fine-tuning. We also demonstrate that pre-training on data from the target domain can lead to significant improvements in a zero-shot scenario. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_08651 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Prompt-Based Approach for Czech Sentiment Analysis Šmíd, Jakub Přibáň, Pavel Computation and Language This paper introduces the first prompt-based methods for aspect-based sentiment analysis and sentiment classification in Czech. We employ the sequence-to-sequence models to solve the aspect-based tasks simultaneously and demonstrate the superiority of our prompt-based approach over traditional fine-tuning. In addition, we conduct zero-shot and few-shot learning experiments for sentiment classification and show that prompting yields significantly better results with limited training examples compared to traditional fine-tuning. We also demonstrate that pre-training on data from the target domain can lead to significant improvements in a zero-shot scenario. |
| title | Prompt-Based Approach for Czech Sentiment Analysis |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.08651 |