EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa

TL;DR

EmoBERTa introduces a speaker-aware method for emotion recognition in conversations by prepending speaker info and using RoBERTa, achieving state-of-the-art results with a simple, end-to-end approach.

Contribution

The paper proposes a straightforward speaker-aware technique for ERC using RoBERTa, improving performance without complex modeling.

Findings

Achieved new state-of-the-art on ERC datasets

Simple prepending of speaker info enhances emotion prediction

End-to-end training with minimal modifications

Abstract

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.