EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa
About
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.
Taewoon Kim, Piek Vossen• 2021
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Emotion Recognition in Conversation | IEMOCAP (test) | Weighted Average F1 Score67.42 | 154 | |
| Emotion Recognition in Conversation | MELD | Weighted Avg F165.61 | 137 | |
| Conversational Emotion Recognition | IEMOCAP | Weighted Average F1 Score67.3 | 129 | |
| Emotion Recognition | IEMOCAP | -- | 71 | |
| Emotion Detection | MELD (test) | Weighted-F10.652 | 32 | |
| Emotion Recognition in Conversation | MELD 1.0 (test) | Weighted F165.61 | 17 | |
| Emotion Recognition in Conversation | IEMOCAP 1.0 (test) | Weighted F1 Score68.57 | 17 | |
| Multimodal Emotion Recognition in Conversation | MELD | Neutral Accuracy78.9 | 12 | |
| Coarse Sentiment Classification | Hotel Review dataset | Coarse Acc81.18 | 12 | |
| Fine Sentiment Classification | Hotel Review dataset | F-Score Accuracy66.7 | 12 |
Showing 10 of 11 rows