# Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks Source: [Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks]() Collection index: [llms.txt]() Data updated: 2026-03-06T05:00:05.533Z Authors: Jakub \\v{S}m\\'id, Pavel P\\v{r}ib\\'a\\v{n}, Pavel Kr\\'al Published: 2026-02-26T08:13:42.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Aspect Sentiment Quad Prediction on Czech monolingual](): Aspect Sentiment Quad Prediction (ASQP); Czech monolingual; F1 Score: not recorded. - [Aspect Sentiment Triplet Extraction on Czech monolingual](): Aspect Sentiment Triplet Extraction (ASTE); Czech monolingual; F1 Score: not recorded. - [Aspect-Category-Opinion-Sentiment (ACOS) on Czech monolingual](): Aspect-Category-Opinion-Sentiment (ACOS); Czech monolingual; F1 Score: not recorded. - [Aspect Sentiment Quadruplet Prediction on Czech (test)](): Aspect Sentiment Quadruplet Prediction; Czech (test); F1 Score: not recorded. - [Aspect Sentiment Triplet Extraction on Czech (test)](): aspect sentiment triplet extraction; Czech (test); F1 Score: not recorded. - [Aspect-Category-Opinion-Sentiment on Czech (test)](): Aspect-Category-Opinion-Sentiment; Czech (test); F1 Score: not recorded. ## Original sources and implementation [Original paper]() [PDF]()