Towards Conversational Search and Recommendation: System Ask, User Respond
Towards Conversational Search and Recommendation: System Ask, User Respond
复制标题
DOI：
10.1145/3269206.3271776
复制
发表时间：
2018-10
期刊：
影响因子：
--
通讯作者：
Yongfeng Zhang;Xu Chen;Qingyao Ai;Liu Yang;W. Bruce Croft
中科院分区：
文献类型：
--
作者：
Yongfeng Zhang;Xu Chen;Qingyao Ai;Liu Yang;W. Bruce Croft
基于用户-系统对话的对话式搜索和推荐展现出与常规搜索和推荐任务的主要区别在于：1）用户和系统可以通过自然语言对话在任务上进行多轮语义一致的交互，以及2）系统可以理解用户需求或者通过直接向用户询问适当的问题来帮助用户阐明他们的需求。我们认为，能够提出问题，从而主动澄清用户需求是对话式搜索和推荐最重要的优势之一。在本文中，我们提出并评估了一个统一的会话搜索/推荐框架，试图使研究问题可行的标准形式化。具体来说，我们提出了一个系统询问-用户响应（SAUR）的对话式搜索范式，定义了范式的主要组成部分，并设计了一个统一的实现框架的产品搜索和推荐在电子商务中。为了实现这一目标，我们提出了多内存网络（MMN）架构，该架构可以根据电子商务中大规模的用户评论集合进行训练。该系统能够以正确的顺序询问基于方面的问题，以了解用户的需求，同时在对话期间进行（个性化）搜索，并在系统感到自信时提供结果。在真实用户购买数据上的实验验证了对话式搜索和推荐相对于传统搜索和推荐算法在NDCG等标准评估指标方面的优势。
Conversational search and recommendation based on user-system dialogs exhibit major differences from conventional search and recommendation tasks in that 1) the user and system can interact for multiple semantically coherent rounds on a task through natural language dialog, and 2) it becomes possible for the system to understand the user needs or to help users clarify their needs by asking appropriate questions from the users directly. We believe the ability to ask questions so as to actively clarify the user needs is one of the most important advantages of conversational search and recommendation. In this paper, we propose and evaluate a unified conversational search/recommendation framework, in an attempt to make the research problem doable under a standard formalization. Specifically, we propose a System Ask -- User Respond (SAUR) paradigm for conversational search, define the major components of the paradigm, and design a unified implementation of the framework for product search and recommendation in e-commerce. To accomplish this, we propose the Multi-Memory Network (MMN) architecture, which can be trained based on large-scale collections of user reviews in e-commerce. The system is capable of asking aspect-based questions in the right order so as to understand the user needs, while (personalized) search is conducted during the conversation, and results are provided when the system feels confident. Experiments on real-world user purchasing data verified the advantages of conversational search and recommendation against conventional search and recommendation algorithms in terms of standard evaluation measures such as NDCG.