arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.01988cs.CLcs.AI
收藏

面向基于主题的对话的个性化主题选择模型

Personalized Topic Selection Model for Topic-Grounded Dialogue

Huazhong University of Science and Technology(华中科技大学);Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)(华中科技大学与平安财产保险研究联合实验室);Ping An Property & Casualty Insurance company of China(中国平安财产保险股份有限公司);Beijing Institute of Technology(北京理工大学);Brilliance Technology Co. Ltd.(华晨汽车科技有限公司)

Shixuan Fan, Wei Wei, Xiaofei Wen, Xianling Mao, Jixiong Chen, Dangyang Chen

AI总结:

本文提出个性化主题选择模型PETD,通过交互辅助信息、结合全局主题与角色对齐,并引入基于对比学习的角色选择器过滤噪声,有效提升了基于主题对话系统的主题预测准确性与回复质量。

摘要:

最近,基于主题的对话(TGD)系统因其通过主题引导对话主动引导用户完成特定任务的强大能力而变得越来越受欢迎。大多数现有工作孤立地利用辅助信息(例如主题或角色)来增强主题选择能力。然而,由于忽视了这些辅助信息源中的噪声及其相互影响,当前模型倾向于预测用户不感兴趣且与上下文无关的主题。为了构建吸引用户且连贯的对话智能体,我们提出了一种面向基于主题的对话的个性化主题选择模型,名为PETD,该模型考虑了辅助信息的交互作用,以选择性地聚合此类信息,从而更准确地预测后续主题。具体而言,我们评估全局主题与角色之间的相关性,并选择性地结合与用户角色对齐的全局主题。此外,在缺乏相关角色注释的约束下,我们提出了一种基于对比学习的角色选择器,以过滤掉不相关的角色。在整个选择和生成过程中,考虑了各种相关的辅助信息。大量实验表明,我们提出的方法可以生成引人入胜且多样化的回复,在各项评估指标上均优于最先进的基线方法。

英文摘要:

Recently, the topic-grounded dialogue (TGD) system has become increasingly popular as its powerful capability to actively guide users to accomplish specific tasks through topic-guided conversations. Most existing works utilize side information (\eg topics or personas) in isolation to enhance the topic selection ability. However, due to disregarding the noise within these auxiliary information sources and their mutual influence, current models tend to predict user-uninteresting and contextually irrelevant topics. To build user-engaging and coherent dialogue agent, we propose a \textbf{P}ersonalized topic s\textbf{E}lection model for \textbf{T}opic-grounded \textbf{D}ialogue, named \textbf{PETD}, which takes account of the interaction of side information to selectively aggregate such information for more accurately predicting subsequent topics. Specifically, we evaluate the correlation between global topics and personas and selectively incorporate the global topics aligned with user personas. Furthermore, we propose a contrastive learning based persona selector to filter out irrelevant personas under the constraint of lacking pertinent persona annotations. Throughout the selection and generation, diverse relevant side information is considered. Extensive experiments demonstrate that our proposed method can generate engaging and diverse responses, outperforming state-of-the-art baselines across various evaluation metrics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑