ABSTRACT
We propose RelQuest, a conversational product search model based on reinforcement learning to generate questions from product descriptions in each round of the conversation, directly maximizing any desired metrics (i.e., the ultimate goal of the conversation), objectives, or even an arbitrary user satisfaction signal. By enabling systems to ask questions about user needs, conversational product search has gained increasing attention in recent years. Asking the right questions through conversations helps the system collect valuable feedback to create better user experiences and ultimately increase sales. In contrast, existing conversational product search methods are based on an assumption that there is a set of effectively pre-defined candidate questions for each product to be asked. Moreover, they make strong assumptions to estimate the value of questions in each round of the conversation. Estimating the true value of questions in each round of the conversation is not trivial since it is unknown. Experiments on real-world user purchasing data show the effectiveness of RelQuest at generating questions that maximize standard evaluation measures such as NDCG.
Supplemental Material
- Qingyao Ai, Yongfeng Zhang, Keping Bi, Xu Chen, and W Bruce Croft. 2017. Learning a hierarchical embedding model for personalized product search. In SIGIR'17 . 645--654.Google ScholarDigital Library
- Mozhdeh Ariannezhad, Ali Montazeralghaem, Hamed Zamani, and Azadeh Shakery. 2017. Improving retrieval performance for verbose queries via axiomatic analysis of term discrimination heuristic. In SIGIR'17. 1201--1204.Google ScholarDigital Library
- Nicholas J Belkin, Colleen Cool, Adelheit Stein, and Ulrich Thiel. 1995. Cases, scripts, and information-seeking strategies: On the design of interactive information retrieval systems. Expert systems with applications , Vol. 9, 3 (1995), 379--395.Google Scholar
- Keping Bi, Qingyao Ai, Yongfeng Zhang, and W Bruce Croft. 2019. Conversational product search based on negative feedback. In CIKM'19. 359--368.Google ScholarDigital Library
- Haw-Shiuan Chang, Ziyun Wang, Luke Vilnis, and Andrew McCallum. 2017. Distributional inclusion vector embedding for unsupervised hypernymy detection. arXiv preprint arXiv:1710.00880 (2017).Google Scholar
- Christiane Fellbaum. 2010. WordNet. In Theory and applications of ontology: computer applications. Springer, 231--243.Google Scholar
- Jiafeng Guo, Yixing Fan, Qingyao Ai, and W Bruce Croft. 2016. A deep relevance matching model for ad-hoc retrieval. In CIKM'16. 55--64.Google ScholarDigital Library
- Ayyoob Imani, Amir Vakili, Ali Montazer, and Azadeh Shakery. 2019 a. An Axiomatic Study of Query Terms Order in Ad-hoc Retrieval. In ECIR'19. Springer, 196--202.Google Scholar
- Ayyoob Imani, Amir Vakili, Ali Montazer, and Azadeh Shakery. 2019 b. Deep neural networks for query expansion using word embeddings. In ECIR'19. Springer, 203--210.Google ScholarDigital Library
- Kalervo J"arvelin and Jaana Kek"al"ainen. 2002. Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems (TOIS) , Vol. 20, 4 (2002), 422--446.Google ScholarDigital Library
- Maryam Karimzadehgan and ChengXiang Zhai. 2011. Improving retrieval accuracy of difficult queries through generalizing negative document language models. In CIKM'11. 27--36.Google ScholarDigital Library
- Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR'15 (San Diego, CA, USA).Google Scholar
- Vijay R Konda and John N Tsitsiklis. 2000. Actor-critic algorithms. In Advances in neural information processing systems. 1008--1014.Google Scholar
- Karol Kurach, Anton Raichuk, Piotr Sta'nczyk, Micha? Zajka c, Olivier Bachem, Lasse Espeholt, Carlos Riquelme, Damien Vincent, Marcin Michalski, Olivier Bousquet, et al. 2020. Google research football: A novel reinforcement learning environment. In AAAI'20 , Vol. 34. 4501--4510.Google ScholarCross Ref
- John Lafferty and Chengxiang Zhai. 2001. Document language models, query models, and risk minimization for information retrieval. In SIGIR'01. 111--119.Google ScholarDigital Library
- Wenqiang Lei, Xiangnan He, Yisong Miao, Qingyun Wu, Richang Hong, Min-Yen Kan, and Tat-Seng Chua. 2020. Estimation-action-reflection: Towards deep interaction between conversational and recommender systems. In WSDM'20. 304--312.Google ScholarDigital Library
- Berenike Litz, Hagen Langer, and Rainer Malaka. 2009. Sequential supervised learning for hypernym discovery from Wikipedia. In IC3K'09. Springer, 68--80.Google Scholar
- Zhengdong Lu and Hang Li. 2013. A deep architecture for matching short texts. Advances in neural information processing systems , Vol. 26 (2013), 1367--1375.Google Scholar
- Ali Montazeralghaem, James Allan, and Philip S Thomas. 2021. Large-scale Interactive Conversational Recommendation System using Actor-Critic Framework. In RecSys'21. 220--229.Google Scholar
- Ali Montazeralghaem, Razieh Rahimi, and James Allan. 2020 a. Relevance Ranking Based on Query-Aware Context Analysis. Advances in Information Retrieval , Vol. 12035 (2020), 446.Google Scholar
- Ali Montazeralghaem, Hamed Zamani, and James Allan. 2020 b. A reinforcement learning framework for relevance feedback. In SIGIR'20. 59--68.Google ScholarDigital Library
- Ali Montazeralghaem, Hamed Zamani, and Azadeh Shakery. 2016. Axiomatic analysis for improving the log-logistic feedback model. In SIGIR'16 . 765--768.Google ScholarDigital Library
- Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Jingfang Xu, and Xueqi Cheng. 2017. Deeprank: A new deep architecture for relevance ranking in information retrieval. In CIKM'17 . 257--266.Google ScholarDigital Library
- Romain Paulus, Caiming Xiong, and Richard Socher. 2017. A deep reinforced model for abstractive summarization. arXiv preprint arXiv:1705.04304 (2017).Google Scholar
- Ivaylo Popov, Nicolas Heess, Timothy Lillicrap, Roland Hafner, Gabriel Barth-Maron, Matej Vecerik, Thomas Lampe, Yuval Tassa, Tom Erez, and Martin Riedmiller. 2017. Data-efficient deep reinforcement learning for dexterous manipulation. arXiv preprint arXiv:1704.03073 (2017).Google Scholar
- Peng Qi, Yuhao Zhang, and Christopher D Manning. 2020. Stay hungry, stay focused: Generating informative and specific questions in information-seeking conversations. arXiv preprint arXiv:2004.14530 (2020).Google Scholar
- Francesco Ricci, Lior Rokach, and Bracha Shapira. 2011. Introduction to recommender systems handbook. In Recommender systems handbook . Springer, 1--35.Google Scholar
- Stephen E Robertson and Steve Walker. 1994. Some simple effective approximations to the 2-poisson model for probabilistic weighted retrieval. In SIGIR'94. Springer, 232--241.Google ScholarCross Ref
- J. J. Rocchio. 1971. Relevance feedback in information retrieval. In The Smart retrieval system - experiments in automatic document processing , , G. Salton (Ed.). Englewood Cliffs, NJ: Prentice-Hall, 313--323.Google Scholar
- David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. 1986. Learning representations by back-propagating errors. nature , Vol. 323, 6088 (1986), 533.Google ScholarDigital Library
- David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al. 2016. Mastering the game of Go with deep neural networks and tree search. nature , Vol. 529, 7587 (2016), 484.Google Scholar
- David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, et al. 2017a. Mastering the game of Go without human knowledge. Nature , Vol. 550, 7676 (2017), 354.Google Scholar
- David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, et al. 2017b. Mastering the game of go without human knowledge. Nature , Vol. 550, 7676 (2017), 354--359.Google Scholar
- Yueming Sun and Yi Zhang. 2018. Conversational recommender system. In SIGIR'18. 235--244.Google ScholarDigital Library
- Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction .MIT press.Google ScholarDigital Library
- Christophe Van Gysel, Maarten de Rijke, and Evangelos Kanoulas. 2016. Learning latent vector spaces for product search. In CIKM'16. 165--174.Google ScholarDigital Library
- Lakshmi Vikraman, Ali Montazeralghaem, Helia Hashemi, W Bruce Croft, and James Allan. 2021. Passage Similarity and Diversification in Non-factoid Question Answering. In ICTIR'21 . 271--280.Google Scholar
- Yansen Wang, Chenyi Liu, Minlie Huang, and Liqiang Nie. 2018. Learning to ask questions in open-domain conversational systems with typed decoders. arXiv preprint arXiv:1805.04843 (2018).Google Scholar
- Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning , Vol. 8, 3--4 (1992), 229--256.Google Scholar
- Liu Yang, Hamed Zamani, Yongfeng Zhang, Jiafeng Guo, and W Bruce Croft. 2017. Neural matching models for question retrieval and next question prediction in conversation. arXiv preprint arXiv:1707.05409 (2017).Google Scholar
- Adams Wei Yu, David Dohan, Minh-Thang Luong, Rui Zhao, Kai Chen, Mohammad Norouzi, and Quoc V Le. 2018. Qanet: Combining local convolution with global self-attention for reading comprehension. arXiv preprint arXiv:1804.09541 (2018).Google Scholar
- Yongfeng Zhang, Xu Chen, Qingyao Ai, Liu Yang, and W Bruce Croft. 2018. Towards conversational search and recommendation: System ask, user respond. In CIKM'18 . 177--186.Google ScholarDigital Library
- Jie Zou, Yifan Chen, and Evangelos Kanoulas. 2020. Towards question-based recommender systems. In SIGIR'20. 881--890.Google ScholarDigital Library
- Jie Zou and Evangelos Kanoulas. 2019. Learning to ask: Question-based sequential Bayesian product search. In CIKM'19 . 369--378.Google ScholarDigital Library
Index Terms
- Learning Relevant Questions for Conversational Product Search using Deep Reinforcement Learning
Recommendations
Extracting Relevant Information from User's Utterances in Conversational Search and Recommendation
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningConversational search and recommendation systems can ask clarifying questions through the conversation and collect valuable information from users. However, an important question remains: how can we extract relevant information from the user's ...
Learning to Ask: Conversational Product Search via Representation Learning
Online shopping platforms, such as Amazon and AliExpress, are increasingly prevalent in society, helping customers purchase products conveniently. With recent progress in natural language processing, researchers and practitioners shift their focus from ...
Conversational Agents: Acting on the Wave of Research and Development
CHI EA '19: Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing SystemsIn the last five years, work on software that interacts with people via typed or spoken natural language, called chatbots, intelligent assistants, social bots, virtual companions, non-human players, and so on, increased dramatically. Chatbots burst into ...
Comments