arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.09102cs.IR
收藏

Estimation-Action-Reflection:会话系统和推荐系统的深度交互

Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems

Wenqiang Lei, Xiangnan He, Yisong Miao, Qingyun Wu, Richang Hong, Min-Yen Kan, Tat-Seng Chua

摘要:

推荐系统采用会话技术动态获取用户偏好,并克服其静态模型的固有局限性。一个成功的会话式推荐系统(CRS)需要正确处理会话和推荐之间的交互。我们认为,需要解决三个基本问题:1)问什么问题的项目属性,2)何时推荐项目,3)如何适应用户的在线反馈。据我们所知,缺乏一个解决这些问题的统一框架。在这项工作中,我们提出了一个新的CRS框架,名为估计-行动-反思,或CRS,它包括三个阶段,以更好地与用户交谈,以填补这一缺失的交互框架的差距。(1)估计,它建立预测模型来估计用户对项目和项目属性的偏好;(2)动作,它学习对话策略,以确定是否询问属性或推荐项目,基于估计阶段和会话历史;以及(3)反射,当用户拒绝Action阶段提出的建议时,它更新推荐模型。我们提出了两个对话的情况下,二进制和枚举的问题,并进行广泛的实验,从Yelp和LastFM的两个数据集,为每个场景,分别。我们的实验表明,与最先进的方法CRM [32]相比,显着改进,对应于更少的会话回合和更高水平的推荐命中率。

英文摘要:

Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models. A successful Conversational Recommender System (CRS) requires proper handling of interactions between conversation and recommendation. We argue that three fundamental problems need to be solved: 1) what questions to ask regarding item attributes, 2) when to recommend items, and 3) how to adapt to the users' online feedback. To the best of our knowledge, there lacks a unified framework that addresses these problems. In this work, we fill this missing interaction framework gap by proposing a new CRS framework named Estimation-Action-Reflection, or EAR, which consists of three stages to better converse with users. (1) Estimation, which builds predictive models to estimate user preference on both items and item attributes; (2) Action, which learns a dialogue policy to determine whether to ask attributes or recommend items, based on Estimation stage and conversation history; and (3) Reflection, which updates the recommender model when a user rejects the recommendations made by the Action stage. We present two conversation scenarios on binary and enumerated questions, and conduct extensive experiments on two datasets from Yelp and LastFM, for each scenario, respectively. Our experiments demonstrate significant improvements over the state-of-the-art method CRM [32], corresponding to fewer conversation turns and a higher level of recommendation hits.

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。

↑