Abstract | ||
---|---|---|
Recent NLP breakthroughs have significantly advanced the state of emotion classification (EC) over text data. However, current treatments guide learning by traditional performance metrics, such as classification error rate, which are not suitable for the highly-imbalanced EC problems; in fact, EC models are predominantly evaluated by variations of the F-measure, recognizing the data imbalance. This paper addresses the dissonance between the learning objective and the performance evaluation for EC with moderate to severe data imbalance. We propose a series of increasingly powerful algorithms for F-measure improvement. An ablation study demonstrates the superiority of learning an optimal class decision threshold. Increased performance is demonstrated when joint learning is carried out over both the representation and the class decision thresholds. Thorough empirical evaluation on benchmark EC datasets that span the spectrum of number of classes and class imbalance shows clear F-measure improvements over baseline models, with good improvements over pre-trained deep models and higher improvements over untrained deep architectures. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1007/978-3-031-15919-0_14 | ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2022, PT I |
Keywords | DocType | Volume |
Emotion classification, Multi-class classification, Class imbalance, F-measure optimization, Transformer models, Deep learning | Conference | 13529 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Toki Tahmid Inan | 1 | 0 | 0.68 |
Mingrui Liu | 2 | 0 | 0.68 |
Amarda Shehu | 3 | 297 | 55.09 |