Prompt-Based Approach for Czech Sentiment Analysis
This work addresses sentiment analysis for Czech, a low-resource language, with incremental improvements using prompt-based methods.
The paper introduces the first prompt-based methods for aspect-based sentiment analysis and sentiment classification in Czech, showing that prompting outperforms traditional fine-tuning and yields significantly better results with limited training examples in zero-shot and few-shot scenarios.
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.