MasonTigers at SemEval-2024 Task 10: Emotion Discovery and Flip Reasoning in Conversation with Ensemble of Transformers and Prompting

TL;DR

This paper details MasonTigers' participation in SemEval-2024 Task 10, employing ensemble transformers and prompting techniques to achieve top rankings in emotion recognition and flip reasoning in monolingual and code-mixed dialogues.

Contribution

The paper introduces novel ensemble transformer and prompting methods for emotion detection and flip reasoning, achieving high accuracy and top rankings in a multilingual conversational analysis shared task.

Findings

F1-score of 0.78 for emotion recognition in Hindi-English dialogues

F1-score of 0.79 for emotion flip reasoning in both Hindi-English and English dialogues

Top rank in emotion recognition and flip reasoning subtasks

Abstract

In this paper, we present MasonTigers' participation in SemEval-2024 Task 10, a shared task aimed at identifying emotions and understanding the rationale behind their flips within monolingual English and Hindi-English code-mixed dialogues. This task comprises three distinct subtasks - emotion recognition in conversation for Hindi-English code-mixed dialogues, emotion flip reasoning for Hindi-English code-mixed dialogues, and emotion flip reasoning for English dialogues. Our team, MasonTigers, contributed to each subtask, focusing on developing methods for accurate emotion recognition and reasoning. By leveraging our approaches, we attained impressive F1-scores of 0.78 for the first task and 0.79 for both the second and third tasks. This performance not only underscores the effectiveness of our methods across different aspects of the task but also secured us the top rank in the first and third subtasks, and the 2nd rank in the second subtask. Through extensive experimentation and analysis, we provide insights into our system's performance and contributions to each subtask.