EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa
We present EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa, a simple yet expressive scheme of solving the ERC (emotion recognition in conversation) task. By simply prepending speaker names to utterances and inserting separation tokens between the utterances in a dialogue, EmoBERTa can learn intra- and inter- speaker states and context to predict the emotion of a current speaker, in an end-to-end manner. Our experiments show that we reach a new state of the art on the two popular ERC datasets using a basic and straight-forward approach. We've open sourced our code and models at https://github.com/tae898/erc.
PDF Abstract
IEMOCAP
MELD
CPED
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Emotion Recognition in Conversation | CPED | EmoBERTa | Accuracy of Sentiment | 48.09 | # 9 | |
| Macro-F1 of Sentiment | 44.60 | # 6 | ||||
| Emotion Recognition in Conversation | IEMOCAP | EmoBERTa | Weighted-F1 | 68.57 | # 22 | |
| Emotion Recognition in Conversation | MELD | EmoBERTa | Weighted-F1 | 65.61 | # 22 |
