Other Roles Matter! Enhancing Role-Oriented Dialogue Summarization via Role Interactions

TL;DR

This paper introduces a novel role interaction method for role-oriented dialogue summarization, leveraging cross and self-attention mechanisms to incorporate information from multiple roles, significantly improving summary quality.

Contribution

It proposes a new role interaction approach using attention mechanisms to enhance dialogue summarization by integrating cross-role information, outperforming existing methods.

Findings

Significant performance improvements over baselines on two datasets

Enhanced summary completeness and topic accuracy

Effective use of cross and self-attention for role interaction

Abstract

Role-oriented dialogue summarization is to generate summaries for different roles in the dialogue, e.g., merchants and consumers. Existing methods handle this task by summarizing each role's content separately and thus are prone to ignore the information from other roles. However, we believe that other roles' content could benefit the quality of summaries, such as the omitted information mentioned by other roles. Therefore, we propose a novel role interaction enhanced method for role-oriented dialogue summarization. It adopts cross attention and decoder self-attention interactions to interactively acquire other roles' critical information. The cross attention interaction aims to select other roles' critical dialogue utterances, while the decoder self-attention interaction aims to obtain key information from other roles' summaries. Experimental results have shown that our proposed method significantly outperforms strong baselines on two public role-oriented dialogue summarization datasets. Extensive analyses have demonstrated that other roles' content could help generate summaries with more complete semantics and correct topic structures.