Large Language Models for Cross-lingual Emotion Detection

TL;DR

This paper describes a cross-lingual emotion detection system using ensemble large language models, achieving superior performance in the WASSA 2024 Task 2 and providing insights into model strengths and limitations.

Contribution

It introduces an ensemble approach with large language models for cross-lingual emotion detection, outperforming previous methods and offering detailed analysis and future directions.

Findings

Outperformed other submissions with a large margin

Demonstrated the effectiveness of model ensembling in emotion detection

Provided comprehensive error analysis and model comparison

Abstract

This paper presents a detailed system description of our entry for the WASSA 2024 Task 2, focused on cross-lingual emotion detection. We utilized a combination of large language models (LLMs) and their ensembles to effectively understand and categorize emotions across different languages. Our approach not only outperformed other submissions with a large margin, but also demonstrated the strength of integrating multiple models to enhance performance. Additionally, We conducted a thorough comparison of the benefits and limitations of each model used. An error analysis is included along with suggested areas for future improvement. This paper aims to offer a clear and comprehensive understanding of advanced techniques in emotion detection, making it accessible even to those new to the field.