Abstract
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.
Abstract (translated)
本文介绍了一个新颖的面向餐厅领域的基于方面的情感分析(ABSA)捷克语数据集,并辅以意见术语注释。该数据集支持三种涉及意见术语的不同难度级别的ABS任务。利用此数据集,我们使用现代Transformer模型(包括大规模语言模型(LLMs)),在单语、跨语和多语环境中进行了广泛的实验。为了解决跨语言挑战,我们提出了一种利用LLMs的翻译和标签对齐方法,并取得了持续改进的效果。我们的研究结果强调了当前最先进模型的优点和局限性,尤其是在处理像捷克语这样的低资源语言的复杂语言特性时。 详细错误分析揭示了一些关键挑战,包括检测细微的意见术语以及细腻的情感表达。该数据集为捷克语ABS领域建立了新的基准,并且我们提出的翻译对齐方法为将ABS资源适应其他低资源语言提供了一种可扩展的解决方案。
URL
https://arxiv.org/abs/2602.22730