The Classics at SemEval-2026 Task 3: Combining Transformer Models and LLM-Generated Annotations for Dimensional Aspect-Based Sentiment Analysis
2026-07-03 • Computation and Language
Computation and Language
AI summaryⓘ
The authors worked on a challenge about understanding fine emotions in text, not just if something is good or bad but how positive and intense it is. They tried two main things: guessing these emotion scores for given parts of text, and finding all opinion details plus their scores. For guessing numbers, they combined different transformer models, and for Russian text, they added extra help by creating synthetic sentiment descriptions using a large language model. To find opinion details and scores together, they trained a decoder model to predict structured information from the text.
Sentiment AnalysisAspect-Based Sentiment AnalysisTransformer ModelsLarge Language Model (LLM)ValenceArousalRegression TaskStructured PredictionNatural Language ProcessingSynthetic Data Generation
Authors
Rafif Alshawi, Amit Raj, Aleksey Kudelya, Alexander Shirnin
Abstract
This paper presents an approach to the SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis. We investigate methods for moving beyond traditional categorical sentiment (e.g., positive or negative) to predict fine-grained, real-valued scores for sentiment "valence" (positivity) and "arousal" (intensity). We participate in two subtasks: predicting these scores for given aspects (Subtask 1) and extracting full sets of sentiment details, including aspects, categories, and opinions alongside their scores (Subtask 3). Our approach for the regression task involves a weighted ensemble of transformer-based encoder models. For the Russian language, we further enhance the input by using a large language model (LLM) to generate synthetic sentiment descriptions. For the extraction task, we fine-tune a decoder LLM to perform structured prediction, allowing the system to identify sentiment elements and estimate their numerical scores simultaneously.