2025/02/24 by Jang, Yoonjin, Kim, Keunha, Youngjoong Ko +1
Computer Science · #Speech and dialogue systems
paper · pdf · doi:10.48550/arxiv.2502.16920
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 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 SS-MPC achieves 15.60% BLEU-1 and 12.44% ROUGE-L score, outperforming the current state-of-the-art MPC response generation model by 3.91%p in BLEU-1 and 0.62%p in ROUGE-L. Additionally, human evaluation confirms that SS-MPC generates more fluent and accurate responses compared to existing MPC models.