EmpTransfo: A Multi-head Transformer Architecture for Creating Empathetic Dialog Systems

TL;DR

EmpTransfo introduces a multi-head Transformer architecture leveraging emotion history and metadata to enhance empathetic responses in dialog systems, outperforming existing models on key metrics.

Contribution

The paper proposes EmpTransfo, a novel Transformer-based model that incorporates emotion history and metadata for more empathetic and context-aware dialogue generation.

Findings

Outperforms other models in Hit@1 metric

Achieves lower perplexity (PPL) indicating better language modeling

Utilizes pre-trained models like OpenAI-GPT effectively

Abstract

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).