Fine-tuning BERT yields micro-F1 scores of 79.1% on Friends and 86.2% on EmotionPush test sets for four-class emotion classification in the EmotionX-2019 shared task.
Attnconvnet at semeval-2018 task 1: Attention-based convolutional neural networks for multi- label emotion classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EmotionX-HSU: Adopting Pre-trained BERT for Emotion Classification
Fine-tuning BERT yields micro-F1 scores of 79.1% on Friends and 86.2% on EmotionPush test sets for four-class emotion classification in the EmotionX-2019 shared task.