Advancing Cross-Lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models
Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART (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.
Authors
BibTex
Bibtex: @conference{icaart25, author={Jakub Šmíd and Pavel P\v{r}ibáň 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}, issn={2184-433X}, }
