Empaths at SemEval-2025 Task 11: Retrieval-Augmented Approach to Perceived Emotions Prediction
This work addresses emotion detection in text for NLP applications, but it is incremental as it builds on existing methods for a specific competition task.
The paper tackled the problem of detecting perceived emotions in text for a SemEval task by proposing EmoRAG, a retrieval-augmented system that uses an ensemble of models without additional training, achieving results comparable to the best systems while being more efficient and scalable.
This paper describes EmoRAG, a system designed to detect perceived emotions in text for SemEval-2025 Task 11, Subtask A: Multi-label Emotion Detection. We focus on predicting the perceived emotions of the speaker from a given text snippet, labeling it with emotions such as joy, sadness, fear, anger, surprise, and disgust. Our approach does not require additional model training and only uses an ensemble of models to predict emotions. EmoRAG achieves results comparable to the best performing systems, while being more efficient, scalable, and easier to implement.