paper-with-me

Papers

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

2022-05-26 · ACL 2022 5 · Haitao Lin, Junnan Zhu, Lu Xiang, Yu Zhou, Jiajun Zhang, Chengqing Zong

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.

📄 PDF Abstract BibTeX arXiv:2205.13190

Code (2)

atulkum/pointer_summarizer 공식 구현 pytorch
xiaolinandy/rods 공식 구현 pytorch

Tasks

Decoder

Similar Papers 제목 키워드 기반

An Organizationally-Oriented Approach to Enhancing Explainability and Control in Multi-Agent Reinforcement Learning

2025-03-30 · Julien Soulé, Jean-Paul Jamont, Michel Occello, Louis-Marie Traonouez 외

Multi-Agent Reinforcement Learning can lead to the development of collaborative agent behaviors that show similarities with organizational concepts. Pushing forward this perspective, we introduce a novel framework that e…

Multi-agent Reinforcement Learning

A Survey on Role-Oriented Network Embedding

2021-07-18 · Pengfei Jiao, Xuan Guo, Ting Pan, Wang Zhang 외

Recently, Network Embedding (NE) has become one of the most attractive research topics in machine learning and data mining. NE approaches have achieved promising performance in various of graph mining tasks including lin…

ClusteringGraph MiningLink PredictionNetwork Embedding+3

Doing the right thing (or not) in a lemons-like situation: on the role of social preferences and Kantian moral concerns

2024-05-21 · Ingela Alger, José Ignacio Rivero-Wildemauwe

We conduct a laboratory experiment using framing to assess the willingness to ``sell a lemon'', i.e., to undertake an action that benefits self but hurts the other (the ``buyer''). We seek to disentangle the role of othe…

Logic-Guided Multistage Inference for Explainable Multidefendant Judgment Prediction

2026-01-19 · Xu Zhang, Qinghua Wang, Mengyang Zhao, Fang Wang 외 arxiv

Crime disrupts societal stability, making law essential for balance. In multidefendant cases, assigning responsibility is complex and challenges fairness, requiring precise role differentiation. However, judicial phrasin…

Does Role Specialization Matter for Explanation Faithfulness in Mixture-of-Experts?

2026-06-28 · Yeji Kim, Housam Babiker, Mi-Young Kim, Randy Goebel arxiv

Mixture-of-Experts (MoE) architectures have recently been extended with role-based mechanisms for interpretability. This is typically done by assigning semantic roles to individual expert components, for example roles li…