Towards Conversational Search and Recommendation: System Ask, User Respond

By Yongfeng Zhang, Xu Chen, Qingyao Ai, Liu Yang, W. Bruce Croft. International Conference on Information and Knowledge Management, 2018

451 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/3ae5bef6b0c8317603a2deab2527383580904fd8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Open-Retrieval Conversational Question Answering (2020, background): “In addition to the ConvQA work mentioned above, researchers are also actively working on other conversation tasks, including conversational recommendation and product search [3, 60], user intent prediction [32], and question retrieval [52].”
Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion (2020, background): “Recently, several studies started to integrate the two components for understanding users’ needs and recommend the right items through natural language conversation [16, 26, 35].”
Lifelong and Interactive Learning of Factual Knowledge in Dialogues (2019, background): “, 2014), conversational recommendation systems (Anelli et al., 2018; Zhang et al., 2018), information-seeking conversational agents (Yang et al.”
When large language models meet personalization: perspectives of challenges and opportunities (2023, unknown): “One direct scenario is the conversational search and recommendation [40].”
Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach (2023, unknown): “To enhance the readability, we make some modifications to the original instructions that are used in our experiments.”
Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5) (2022, background): “[69] Yongfeng Zhang, Xu Chen, Qingyao Ai, Liu Yang, and W Bruce Croft.”
Answer Interaction in Non-factoid Question Answering Systems (2019, background): “n, several works [19, 26, 27, 30, 31] observed and studied information-seeking conversations between humans and addressed different facets of such interactions. Finally, conversational recommendation [40] and response ranking [36] have been explored under this multi-turn interaction setting. 3 OUR A”
Domain-specific Genetic Algorithm for Multi-tenant DNNAccelerator Scheduling (2021, background): “First, end applications (such as AR/VR [55] or self-driving [16, 117]) and cloud services (such as search [36, 124] and translation [58, 62]) often rely on several DNN models internally.”
A Survey on Conversational Recommender Systems (2020, background): “s retailers [46]. A smartphone database consisting of 1721 products with multiple features [34]. Amazon electronics review dataset5 containing millions of products, user reviews and product meta-data [164]. A dataset consisting of 120 personal computers, each with 8 features [128]. Travel More than ”
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations (2019, unknown): “[53] automatically extracted facet-value pairs from product reviews and considered them as questions and answers.”
Explainable Product Search with a Dynamic Relation Embedding Model (2019, background): “Zhang et al. [73] and Bi et al. [9] also extract product aspects from review data and build embedding networks that encodes both items and their extracted aspects for conversational product search and recommendation.”
Continuous and Interactive Factual Knowledge Learning in Veriﬁcation Dialogues (2020, background): “Recently, many conversational systems have been proposed, e.g., Conversational Recommender Systems [46, 1, 58] and Information-seeking Conversation [55, 40].”
Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search (2020, background): “There have been recent efforts to go beyond the “user asks, system responds” paradigm by asking clarifying questions from the users, including offline evaluation of search clarification [1], clarifying question generation for opendomain search queries [61], and preference elicitation in conversation”
Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems (2020, methodology): “hrough conversations with users. This possibility is envisioned as the conversational recommender system (CRS), for which the community has started to expend effort in exploring its various settings. [40] built a conversational search engine by focusing on document representation. [23] developed a d”
Advances and Challenges in Conversational Recommender Systems: A Survey (2021, methodology): “Fitting historical patterns Sequential neural network Providing preferred attribute values Yes [31, 207]”
MIMICS: A Large-Scale Data Collection for Search Clarification (2020, background): “It has lately attracted much attention in information seeking systems, such as search engines (similar to this study) [29] and recommender systems [32].”