Advancing Cross-Lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models

Jakub Šmíd, Jakub Šmíd, Pavel Přibáň, Pavel Král

2025

Abstract

Aspect-based sentiment analysis (ABSA) has made significant strides, yet challenges remain for low-resource languages due to the predominant focus on English. Current cross-lingual ABSA studies often centre on simpler tasks and rely heavily on external translation tools. In this paper, we present a novel sequence-to-sequence method for compound ABSA tasks that eliminates the need for such tools. Our approach, which uses constrained decoding, improves cross-lingual ABSA performance by up to 10%. This method broadens the scope of cross-lingual ABSA, enabling it to handle more complex tasks and providing a practical, efficient alternative to translation-dependent techniques. Furthermore, we compare our approach with large language models (LLMs) and show that while fine-tuned multilingual LLMs can achieve comparable results, English-centric LLMs struggle with these tasks.

Paper Citation

in Harvard Style

Šmíd J., Přibáň P. and Král P. (2025). Advancing Cross-Lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 757-766. DOI: 10.5220/0013349400003890

in Bibtex Style

@conference{icaart25,
author={Jakub Šmíd and Pavel Přibáň and Pavel Král},
title={Advancing Cross-Lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={757-766},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013349400003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Advancing Cross-Lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models
SN - 978-989-758-737-5
AU - Šmíd J.
AU - Přibáň P.
AU - Král P.
PY - 2025
SP - 757
EP - 766
DO - 10.5220/0013349400003890
PB - SciTePress