AILS-NTUA at SemEval-2026 Task 3: Efficient Dimensional Aspect-Based Sentiment Analysis
This work provides an incremental improvement in aspect-based sentiment analysis for researchers and practitioners working with multilingual and multi-domain sentiment data.
This paper presents the AILS-NTUA system for Dimensional Aspect-Based Sentiment Analysis (DimABSA), addressing sentiment regression, triplet extraction, and quadruplet prediction across multiple languages and domains. The system achieved competitive performance, consistently surpassing baselines in most evaluation settings.
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.