Towards Conversational Search and Recommendation: System Ask, User Respond

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.

[1]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[2]  W. Bruce Croft,et al.  I 3 R: a new approach to the design of document retrieval systems , 1987 .

[3]  W. Bruce Croft,et al.  I3R: A new approach to the design of document retrieval systems , 1987, J. Am. Soc. Inf. Sci..

[4]  Nicholas J. Belkin,et al.  Cases, scripts, and information-seeking strategies: On the design of interactive information retrieval systems , 1995 .

[5]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[6]  James Allan,et al.  A comparison of statistical significance tests for information retrieval evaluation , 2007, CIKM '07.

[7]  Lior Rokach,et al.  Recommender Systems Handbook , 2010 .

[8]  W. B. Lee,et al.  Multi-facet product information search and retrieval using semantically annotated product family ontology , 2010, Inf. Process. Manag..

[9]  ChengXiang Zhai,et al.  Supporting Keyword Search in Product Database: A Probabilistic Approach , 2013, Proc. VLDB Endow..

[10]  ChengXiang Zhai,et al.  A probabilistic mixture model for mining and analyzing product search log , 2013, CIKM.

[11]  Jure Leskovec,et al.  Hidden factors and hidden topics: understanding rating dimensions with review text , 2013, RecSys.

[12]  Milica Gasic,et al.  POMDP-Based Statistical Spoken Dialog Systems: A Review , 2013, Proceedings of the IEEE.

[13]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[14]  Matthew Henderson,et al.  Deep Neural Network Approach for the Dialog State Tracking Challenge , 2013, SIGDIAL Conference.

[15]  Yiqun Liu,et al.  Do users rate or review?: boost phrase-level sentiment labeling with review-level sentiment classification , 2014, SIGIR.

[16]  Guokun Lai,et al.  Explicit factor models for explainable recommendation based on phrase-level sentiment analysis , 2014, SIGIR.

[17]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[18]  Alex Graves,et al.  Neural Turing Machines , 2014, ArXiv.

[19]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[20]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

[21]  Jure Leskovec,et al.  Inferring Networks of Substitutable and Complementary Products , 2015, KDD.

[22]  Jason Weston,et al.  Large-scale Simple Question Answering with Memory Networks , 2015, ArXiv.

[23]  Jason Weston,et al.  Memory Networks , 2014, ICLR.

[24]  Jiafeng Guo,et al.  Analysis of the Paragraph Vector Model for Information Retrieval , 2016, ICTIR.

[25]  Jason Weston,et al.  Dialog-based Language Learning , 2016, NIPS.

[26]  Richard Socher,et al.  Ask Me Anything: Dynamic Memory Networks for Natural Language Processing , 2015, ICML.

[27]  Filip Radlinski,et al.  Towards Conversational Recommender Systems , 2016, KDD.

[28]  Jason Weston,et al.  Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks , 2015, ICLR.

[29]  Jason Weston,et al.  Key-Value Memory Networks for Directly Reading Documents , 2016, EMNLP.

[30]  Xiang Zhang,et al.  Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems , 2015, ICLR.

[31]  Yelong Shen,et al.  ReasoNet: Learning to Stop Reading in Machine Comprehension , 2016, CoCo@NIPS.

[32]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[33]  M. de Rijke,et al.  Learning Latent Vector Spaces for Product Search , 2016, CIKM.

[34]  Richard Socher,et al.  Dynamic Memory Networks for Visual and Textual Question Answering , 2016, ICML.

[35]  Daniel McDuff,et al.  MISC: A data set of information-seeking conversations , 2017 .

[36]  W. Bruce Croft,et al.  Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation , 2017, ArXiv.

[37]  David Vandyke,et al.  A Network-based End-to-End Trainable Task-oriented Dialogue System , 2016, EACL.

[38]  W. Bruce Croft,et al.  Learning a Hierarchical Embedding Model for Personalized Product Search , 2017, SIGIR.

[39]  Jason Weston,et al.  Learning Through Dialogue Interactions , 2016, ICLR.

[40]  M. de Rijke,et al.  Attentive Memory Networks: Efficient Machine Reading for Conversational Search , 2017, ArXiv.

[41]  W. Bruce Croft,et al.  A Language Modeling Approach to Information Retrieval , 1998, SIGIR Forum.

[42]  Mark Sanderson,et al.  How Do People Interact in Conversational Speech-Only Search Tasks: A Preliminary Analysis , 2017, CHIIR.

[43]  Filip Radlinski,et al.  A Theoretical Framework for Conversational Search , 2017, CHIIR.

[44]  Mark Sanderson,et al.  Extracting audio summaries to support effective spoken document search , 2017, J. Assoc. Inf. Sci. Technol..

[45]  Jason Weston,et al.  Learning End-to-End Goal-Oriented Dialog , 2016, ICLR.

[46]  Jun Huang,et al.  Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems , 2018, SIGIR.