looploop at SemEval-2026 Task 3: A Dimensional Aspect-Based Sentiment System with DeBERTa Regression and Qwen3 Instruction Fine-Tuning
Year: 2026
Type: conference-paper
Abstract: Aspect-Based Sentiment Analysis (ABSA) has evolved to capture continuous affective states, posing challenges for traditional classification models.We adopt a hybrid approach tailored to the varying complexities of the subtasks.For Task 1 (Valence-Arousal Regression), we employ a discriminative architecture using pretrained DeBERTa encoder with a MeanPooling mechanism to directly regress continuous sentiment scores.For Tasks 2 and 3, which require complex structural extraction of opinion triplets and quadruplets, we utilize a generative approach by fine-tuning the Qwen3-4B-Instruct large language model via 4-bit QLoRA.Our system effectively handles both precise numerical regression and complex structural text generation, achieving competitive results across the English laptop and restaurant domains.
Institution: Yunnan University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166814504