EmpTransfo: A Multi-head Transformer Architecture for Creating Empathetic Dialog Systems
This work addresses the problem of generating emotionally appropriate responses in dialog systems, which is incremental as it builds on existing pre-trained models.
The paper tackled the challenge of creating empathetic dialog systems by proposing EmpTransfo, a multi-head Transformer architecture that leverages emotion history and metadata, resulting in improved performance with higher Hit@1 and lower Perplexity compared to other models.
Understanding emotions and responding accordingly is one of the biggest challenges of dialog systems. This paper presents EmpTransfo, a multi-head Transformer architecture for creating an empathetic dialog system. EmpTransfo utilizes state-of-the-art pre-trained models (e.g., OpenAI-GPT) for language generation, though models with different sizes can be used. We show that utilizing the history of emotions and other metadata can improve the quality of generated conversations by the dialog system. Our experimental results using a challenging language corpus show that the proposed approach outperforms other models in terms of Hit@1 and PPL (Perplexity).