Improving Generative Cross-Lingual Aspect-Based Sentiment Analysis with Constrained Decoding


Jakub Šmíd and Pavel Přibáň and Pavel Král
Lecture Notes in Computer Science; Agents and Artificial Intelligence : 17th International Conference, ICAART 2025, Porto, Portugal, February 23–25, 2025, Revised Selected Papers, Part III (2026)

PDF

Abstract

While aspect-based sentiment analysis (ABSA) has made substantial progress, challenges remain for low-resource languages, which are often overlooked in favour of English. Current cross-lingual ABSA approaches focus on limited, less complex tasks and often rely on external translation tools. This paper introduces a novel approach using constrained decoding with sequence-to-sequence models, eliminating the need for unreliable translation tools and improving cross-lingual performance by 5% on average for the most complex task. The proposed method also supports multi-tasking, which enables solving multiple ABSA tasks with a single model, with constrained decoding boosting results by more than 10%. We evaluate our approach across seven languages and six ABSA tasks, surpassing state-of-the-art methods and setting new benchmarks for previously unexplored tasks. Additionally, we assess large language models (LLMs) in zero-shot, few-shot, and fine-tuning scenarios. While LLMs perform poorly in zero-shot and few-shot settings, fine-tuning achieves competitive results compared to smaller multilingual models, albeit at the cost of longer training and inference times. We provide practical recommendations for real-world applications, enhancing the understanding of cross-lingual ABSA methodologies. This study offers valuable insights into the strengths and limitations of cross-lingual ABSA approaches, advancing the state-of-the-art in this challenging research domain.

Authors

BibTex

Bibtex: @InProceedings{10.1007/978-3-032-25035-3_20, author="{\v{S}}m{\'i}d, Jakub and P{\v{r}}ib{\'a}{\v{n}}, Pavel and Kr{\'a}l, Pavel", editor="van den Herik, H. Jaap and Rocha, Ana Paula and Steels, Luc", title="Improving Generative Cross-Lingual Aspect-Based Sentiment Analysis with Constrained Decoding", booktitle="Agents and Artificial Intelligence", year="2027", publisher="Springer Nature Switzerland", address="Cham", pages="419--446", abstract="While aspect-based sentiment analysis (ABSA) has made substantial progress, challenges remain for low-resource languages, which are often overlooked in favour of English. Current cross-lingual ABSA approaches focus on limited, less complex tasks and often rely on external translation tools. This paper introduces a novel approach using constrained decoding with sequence-to-sequence models, eliminating the need for unreliable translation tools and improving cross-lingual performance by 5{\%} on average for the most complex task. The proposed method also supports multi-tasking, which enables solving multiple ABSA tasks with a single model, with constrained decoding boosting results by more than 10{\%}.", isbn="978-3-032-25035-3" }
Back to Top