Team A at SemEval-2025 Task 11: Breaking Language Barriers in Emotion Detection with Multilingual Models

TL;DR

This paper presents a system for emotion detection in text using multilingual embeddings, achieving robust performance across six emotions and demonstrating the effectiveness of multilingual models in bridging language barriers.

Contribution

The paper introduces a multilingual embedding-based approach for emotion detection, showing improved robustness and accuracy in a multilingual setting compared to monolingual methods.

Findings

Multilingual embeddings enhance emotion detection accuracy.

The best model used multilingual embeddings with a fully connected layer.

Results demonstrate robustness across six emotion categories.

Abstract

This paper describes the system submitted by Team A to SemEval 2025 Task 11, ``Bridging the Gap in Text-Based Emotion Detection.'' The task involved identifying the perceived emotion of a speaker from text snippets, with each instance annotated with one of six emotions: joy, sadness, fear, anger, surprise, or disgust. A dataset provided by the task organizers served as the foundation for training and evaluating our models. Among the various approaches explored, the best performance was achieved using multilingual embeddings combined with a fully connected layer. This paper details the system architecture, discusses experimental results, and highlights the advantages of leveraging multilingual representations for robust emotion detection in text.