SS-MPC: A Sequence-Structured Multi-Party Conversation System

Recent Multi-Party Conversation (MPC) models typically rely on graph-based approaches to capture dialogue structures. However, these methods have limitations, such as information loss during the projection of utterances into structural embeddings and constraints in leveraging pre-trained language models directly. In this paper, we propose $\mathbf{\text{SS-MPC}}$, a response generation model for MPC that eliminates the need for explicit graph structures. Unlike existing models that depend on graphs to analyze conversation structures, SS-MPC internally encodes the dialogue structure as a sequential input, enabling direct utilization of pre-trained language models. Experimental results show that $\mathbf{\text{SS-MPC}}$ achieves $\mathbf{\text{15.60\%}}\mathbf{\text{BLEU-1}}$ and $\mathbf{\text{12.44\%}}\mathbf{\text{ROUGE-L}}$ score, outperforming the current state-of-the-art MPC response generation model by $\mathbf{\text{3.91\%p}}$ in $\mathbf{\text{BLEU-1}}$ and $\mathbf{\text{0.62\%p}}$ in $\mathbf{\text{ROUGE-L}}$. Additionally, human evaluation confirms that SS-MPC generates more fluent and accurate responses compared to existing MPC models.