Abstract
Traditional recommender systems are usually single-shot systems, lacking real-time dialog with customers. Using dialog as an interactive method can more accurately capture user preferences and enhance system transparency. However, building such a goal-oriented dialog system suffered many challenges as the system itself needs to collaborate with various sub-tasks, such as collecting user needs through interaction, recommending appropriate products to users. Most existing work of dialog systems does not comprehensively consider this scenario and the challenges caused. In this paper, we propose a novel memory network framework for conversational recommendation, which harness dialog historical information to endows our model with adaptability in different dialog scenarios, and leverage the knowledge base and user profiles to reweight candidates, to reduce the ambiguity during interactions and improve the quality of conversational recommender systems. Through the experiments on the personalized bAbI dialog dataset and restaurant recommendation application, we demonstrate that the proposed method can achieve state-of-the-art performance in a few classical tasks, such as options display and information provision, etc.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models. In: IJCNLP, pp. 605–614 (2017)
Banchs, R., Li, H.: IRIS: a chat-oriented dialogue system based on the vector space model. In: ACL. pp. 37–42 (2012)
Bi, K., Ai, Q., Zhang, Y., Bruce Croft, W.: Conversational product search based on negative feedback. In: CIKM, pp. 359–368 (2019)
Bordes, A., Lan Boureau, Y., Weston, J.: Learning end-to-end goal-oriented dialog. In: ICLR, pp. 1–15 (2017)
Eric, M., Krishnan, L., Charette, F., Manning, C.D.: Key-value retrieval networks for task-oriented dialogue. In: SIGDIAL, pp. 37–49 (2017)
Gangi Reddy, R., Contractor, D., Raghu, D., Joshi, S.: Multi-level memory for task oriented dialogs. In: ACL, pp. 3744–3754 (2019)
Gao, J., Galley, M., Li, L.: Neural approaches to conversational AI. In: ACL, pp. 2–7 (2018)
He, X., Deng, K., Wang, X., Li, Y., Zhang, Y.D., Wang, M.: LightGCN: simplifying and powering graph convolution network for recommendation. In: SIGIR, pp. 639–648 (2020)
Huang, J., Zhao, W.X., Dou, H., Wen, J.R., Chang, E.Y.: Improving sequential recommendation with knowledge-enhanced memory networks. In: SIGIR, pp. 505–514 (2018)
Joshi, C.K., Mi, F., Faltings, B.: Personalization in goal-oriented dialog. In: NIPS, pp. 2440–2448 (2017)
Lei, W., et al.: Estimation-action-reflection: towards deep interaction between conversational and recommender systems. In: WSDM, pp. 304–312 (2020)
Li, J., Monroe, W., Ritter, A., Galley, M., Gao, J., Jurafsky, D.: Deep reinforcement learning for dialogue generation. In: EMNLP, pp. 1192–1202 (2016)
Lin, Y., Liu, Z., Sun, M., Liu, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: AAAI, pp. 2181–2187 (2015)
Lipton, Z., Li, X., Gao, J., Li, L., Ahmed, F., Deng, L.: BBQ-networks: efficient exploration in deep reinforcement learning for task-oriented dialogue systems. In: AAAI, pp. 5237–5244 (2018)
Liu, F., Perez, J.: Gated end-to-end memory networks. In: EACL, pp. 1–10 (2017)
Luo, L., Huang, W., Zeng, Q., Nie, Z., Sun, X.: Learning personalized end-to-end goal-oriented dialog. In: AAAI, pp. 6794–6801 (2019)
Miller, A.H., Fisch, A., Dodge, J., Karimi, A.H., Bordes, A., Weston, J.: Key-value memory networks for directly reading documents. EMNLP 2016, 1400–1409 (2016)
Sarnobat, A., Kalola, D.: A survey on recommender systems. In: IJSRP, p. 9356 (2019)
Su, F.G., Hsu, A.R., Tuan, Y.L., Lee, H.Y.: Personalized dialogue response generation learned from monologues. In: INTERSPEECH, pp. 4160–4164 (2019)
Sun, Y., Yuan, N.J., Wang, Y., Xie, X., McDonald, K., Zhang, R.: Contextual intent tracking for personal assistants. In: SIGKDD, pp. 273–282 (2016)
Tsumita, D., Takagi, T.: Dialogue based recommender system that flexibly mixes utterances and recommendations. In: WI, pp. 51–58 (2019)
Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998–6008 (2017)
Wang, D., Jojic, N., Brockett, C., Nyberg, E.: Steering output style and topic in neural response generation. In: EMNLP, pp. 2140–2150 (2017)
Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: AAAI, pp. 1112–1119 (2014)
Wen, T.H., et al.: A network-based end-to-end trainable task-oriented dialogue system. In: EACL, pp. 438–449 (2017)
Wu, Y., Wei, F., Huang, S., Wang, Y., Li, Z., Zhou, M.: Response generation by context-aware prototype editing. In: AAAI, pp. 7281–7288 (2019)
Xing, C., et al.: Topic aware neural response generation. In: AAAI, pp. 3351–3357 (2017)
Yang, L., et al.: A hybrid retrieval-generation neural conversation model. In: CIKM, pp. 1341–1350 (2019)
Yang, L., et al.: Response ranking with deep matching networks and external knowledge in information-seeking conversation systems. In: SIGIR, pp. 245–254 (2018)
Zhang, Y., Chen, X., Ai, Q., Yang, L., Bruce Croft, W.: Towards conversational search and recommendation: system ask, user respond. In: CIKM, pp. 177–186 (2018)
Zhao, T., Eskenazi, M.: Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning. In: SIGDIAL, pp. 1–10 (2016)
Acknowledgment
This work is supported by the Beijing Natural Science Foundation under grant 4192008, and the Science Foundation Ireland (SFI) under Grant Number 12/RC/2289_P2.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
He, M., Shen, T., Dong, R. (2021). Conversation and Recommendation: Knowledge-Enhanced Personalized Dialog System. In: Brambilla, M., Chbeir, R., Frasincar, F., Manolescu, I. (eds) Web Engineering. ICWE 2021. Lecture Notes in Computer Science(), vol 12706. Springer, Cham. https://doi.org/10.1007/978-3-030-74296-6_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-74296-6_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-74295-9
Online ISBN: 978-3-030-74296-6
eBook Packages: Computer ScienceComputer Science (R0)