Abstract
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.
Abstract (translated)
本文介绍了首个用于捷克语基于方面的情感分析和情感分类的提示（prompt）方法。我们采用序列到序列模型同时解决基于方面的任务，并展示了我们的提示方法相对于传统微调方法的优势。此外，我们在情感分类中进行了零样本学习和少量样本学习实验，结果显示，在训练示例有限的情况下，使用提示能够显著优于传统的微调方法。另外，我们也证明了在目标领域的数据上进行预训练可以在零样本场景下带来显著的改进。
URL
https://arxiv.org/abs/2508.08651
