Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks
This work provides a new benchmark dataset and a scalable adaptation method for aspect-based sentiment analysis in low-resource languages like Czech, which is important for researchers and developers working on sentiment analysis for less-resourced languages.
This paper introduces a new Czech dataset for aspect-based sentiment analysis (ABSA) in the restaurant domain, which includes annotations for opinion terms. They benchmarked Transformer-based models and LLMs on this dataset, proposing a translation and label alignment methodology using LLMs that consistently improved cross-lingual performance.
This paper introduces a novel Czech dataset in the restaurant domain for aspect-based sentiment analysis (ABSA), enriched with annotations of opinion terms. The dataset supports three distinct ABSA tasks involving opinion terms, accommodating varying levels of complexity. Leveraging this dataset, we conduct extensive experiments using modern Transformer-based models, including large language models (LLMs), in monolingual, cross-lingual, and multilingual settings. To address cross-lingual challenges, we propose a translation and label alignment methodology leveraging LLMs, which yields consistent improvements. Our results highlight the strengths and limitations of state-of-the-art models, especially when handling the linguistic intricacies of low-resource languages like Czech. A detailed error analysis reveals key challenges, including the detection of subtle opinion terms and nuanced sentiment expressions. The dataset establishes a new benchmark for Czech ABSA, and our proposed translation-alignment approach offers a scalable solution for adapting ABSA resources to other low-resource languages.