Abstract
In this paper, we present AILS-NTUA system for Track-A of SemEval-2026 Task 3 on Dimensional Aspect-Based Sentiment Analysis (DimABSA), which encompasses three complementary problems: Dimensional Aspect Sentiment Regression (DimASR), Dimensional Aspect Sentiment Triplet Extraction (DimASTE), and Dimensional Aspect Sentiment Quadruplet Prediction (DimASQP) within a multilingual and multi-domain framework. Our methodology combines fine-tuning of language-appropriate encoder backbones for continuous aspect-level sentiment prediction with language-specific instruction tuning of large language models using LoRA for structured triplet and quadruplet extraction. This unified yet task-adaptive design emphasizes parameter-efficient specialization across languages and domains, enabling reduced training and inference requirements while maintaining strong effectiveness. Empirical results demonstrate that the proposed models achieve competitive performance and consistently surpass the provided baselines across most evaluation settings.
Abstract (translated)
在这篇论文中,我们介绍了AILS-NTUA系统,该系统用于SemEval-2026任务3的Track-A轨道,即维度基础情感分析(DimABSA)中的问题。这个问题包括三个互补的问题:维度属性情感回归(DimASR)、维度属性情感三元组抽取(DimASTE)以及维度属性情感四元组预测(DimASQP),并且这些问题在一个多语言和跨领域框架中进行研究。 我们的方法结合了针对连续属性级别的情感预测对适合各语言的编码器骨干网络进行微调,以及使用LoRA技术对大型语言模型进行特定语言指令调整以提取结构化的三元组和四元组。这种统一但任务适应性的设计强调在不同语言和领域中的参数效率专业化,从而减少训练和推理的需求,并保持强大的效果。 实证结果表明,所提出的模型达到了竞争性性能,在大多数评估设置中都超越了提供的基准方法。
URL
https://arxiv.org/abs/2603.04933