对话推荐算法研究综述
作者:
作者单位:

作者简介:

通讯作者:

黄晓雯,E-mail:xwhuang@bjtu.edu.cn

基金项目:

国家重点研发计划(2018AAA0100604);中央高校基本科研专项资金(2021RC217);北京市自然科学基金(JQ20023);国家自然科学基金(61632002,61832004,62036012,61720106006)


Survey of Conversational Recommendation Algorithms
Author:
Affiliation:

Fund Project:

National Natural Science Foundation of China (K21RC00020)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    推荐系统是一种通过理解用户的兴趣和偏好帮助用户过滤大量无效信息并获取感兴趣的信息或者物品的信息过滤系统.目前主流的推荐系统主要基于离线的、历史的用户数据,不断训练和优化线下模型,继而为在线的用户推荐物品,这类训练方式主要存在三个问题:基于稀疏且具有噪声的历史数据估计用户偏好的不可靠估计、对影响用户行为的在线上下文环境因素的忽略和默认用户清楚自身偏好的不可靠假设.由于对话系统关注于用户的实时反馈数据,获取用户当前交互的意图,因此"对话推荐"通过结合对话形式与推荐任务成为解决传统推荐问题的有效手段.对话推荐将对话系统实时交互的数据获取方式应用到推荐系统中,采用了与传统推荐系统不同的推荐思路,通过利用在线交互信息,引导和捕捉用户当前的偏好兴趣,并及时进行反馈和更新.在过去的几年里,越来越多的研究者开始关注对话推荐系统,这一方面归功于自然语言处理领域中语音助手以及聊天机器人技术的广泛使用,另一方面受益于强化学习、知识图谱等技术在推荐策略中的成熟应用.本文将对话推荐系统的整体框架进行梳理,将对话推荐算法研究所使用的数据集进行分类,同时对评价对话推荐效果的相关指标进行讨论,重点关注于对话推荐系统中的后台对话策略与推荐逻辑,对近年来的对话推荐算法进行综述,最后对对话推荐领域的未来发展方向进行展望.

    Abstract:

    Recommender system is an information filtering system that helps users filter a large number of invalid information to obtain information or items by estimating their interests and preferences. The mainstream traditional recommendation system mainly uses offline and historical user data to continuously train and optimize offline models, and then recommend items for online users. There are three main problems:the unreliable estimation of user preferences based on sparse and noisy historical data, the ignorance of online contextual factors that affect user behavior, and the unreliable assumption that users are aware of their preferences by default. Since the dialogue system focuses on the user's real-time feedback data and obtains the user's current interaction intentions, "conversational recommendation " combines the interactive form of the dialogue system with the recommendation task, and becomes an effective means to solve the traditional recommendation problem. Through online interactive methods, conversational recommendation can guide and capture users' current preferences and interests, and provide timely feedback and updates. Thanks to the widespread use of voice assistants and chatbot technologies, as well as the mature application of technologies such as reinforcement learning and knowledge graphs in recommendation strategies, in the past few years, more and more researchers have paid attention to conversational recommendation systems. This survey combs the overall framework of the conversational recommendation system, classifies the datasets used in the conversational recommendation algorithm, and discusses the relevant metrics to evaluate the effect of the conversational recommendation. Focusing on the background interaction strategy and recommendation logic in conversational recommendation, this survey summarizes the existing research achievements of the domestic and foreign researchers in recent years. And finally, this survey also summarizes and prospects future works of conversational recommendation.

    参考文献
    相似文献
    引证文献
引用本文

赵梦媛,黄晓雯,桑基韬,于剑.对话推荐算法研究综述.软件学报,,():0

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
历史
  • 收稿日期:2021-04-22
  • 最后修改日期:2021-09-22
  • 录用日期:
  • 在线发布日期: 2021-11-24
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号