Transformer based neural networks for emotion recognition in conversations
Preprint
Abstract
This paper outlines the approach of the ISDS-NLP team in the SemEval 2024 Task 10: Emotion Discovery and Reasoning its Flip in Conversation (EDiReF). For Subtask 1 we obtained a weighted F1 score of 0.43 and placed 12 in the leaderboard. We investigate two distinct approaches: Masked Language Modeling (MLM) and Causal Language Modeling (CLM). For MLM, we employ pre-trained BERT-like models in a multilingual setting, fine-tuning them with a classifier to predict emotions. Experiments with varying input lengths, classifier architectures, and fine-tuning strategies demonstrate the effectiveness of this approach. Additionally, we utilize Mistral 7B Instruct V0.2, a state-of-the-art model, applying zero-shot and few-shot prompting techniques. Our findings indicate that while Mistral shows promise, MLMs currently outperform them in sentence-level emotion classification.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling2024
- Discovering emotion and reasoning its flip in multi-party conversations using masked memory network and transformerKnowledge-Based Systems, 2022
- Unsupervised Cross-lingual Representation Learning at Scale2020
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019
- An argument for basic emotionsCognition and Emotion, 1992