conftrace_

2022 ACL ACL 2022

Transformer based ensemble for emotion detection

Abstract

AbstractDetecting emotions in languages is important to accomplish a complete interaction between humans and machines. This paper describes our contribution to the WASSA 2022 shared task which handles this crucial task of emotion detection. We have to identify the following emotions: sadness, surprise, neutral, anger, fear, disgust, joy based on a given essay text. We are using an ensemble of ELECTRA and BERT models to tackle this problem achieving an F1 score of 62.76%. Our codebase (https://bit.ly/WASSA_shared_task) and our WandB project (https://wandb.ai/acl_wassa_pictxmanipal/acl_wassa) is publicly available.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Interdisciplinary

🐣 Hot Topic Early Bird - affective computing

Authors

Aditya Kane, Shantanu Patankar, Sahil Khose, Neeraja Kirtane

Topics

Interdisciplinary > Linguistics > Computational Linguistics Interdisciplinary > Social > Affective Computing Deep Learning > Learning Types > Ensemble Learning Artificial Intelligence > Core AI > Natural Language Processing

Keywords

ensemble learning sentiment analysis natural language processing text classification emotion detection affective computing transformer ensemble transformer model

More from ACL 2022

All ACL 2022 papers →

Continuing Pre-trained Model with Multiple Training Strategies for Emotional Classification

Empathy and Distress Prediction using Transformer Multi-output Regression and Emotion Analysis with an Ensemble of Supervised and Zero-Shot Learning Models

Leveraging Emotion-Specific features to improve Transformer performance for Emotion Classification

Team IITP-AINLPML at WASSA 2022: Empathy Detection, Emotion Classification and Personality Detection

Transformer-based Architecture for Empathy Prediction and Emotion Classification

Prompt-based Pre-trained Model for Personality and Interpersonal Reactivity Prediction