对话推荐旨在通过与用户对话来获取用户偏好并向其推荐高质量的商品,现有的对话推荐系统大多忽略了用户记忆中的潜在兴趣,导致难以在短时间内准确获取用户偏好。针对这一问题,该文提出了基于用户记忆的对话推荐模型,用户记忆包括用户的历史行为序列和评论、对话记录。首先,通过图神经网络学习评论和对话记录中用户、商品和属性之间的关系信息,保证系统能够提出与用户偏好最相关的问题来尽快了解用户当前需求;其次,利用改进的Transformer建模用户多类型行为序列来学习用户潜在兴趣;最后,与学习到的关系信息融合来做出推荐。在包含多个领域的对话数据集上的实验结果表明,该文提出的模型既能获得更高的推荐准确性又能以更少的对话次数成功推荐商品。
Abstract
Conversational recommendation aims to recommend high-quality products through dialogue with users. To utilize the potential interests in user history, we propose a conversational recommendation model based on user memory. User memory includes user's historical behavior sequence, comments and dialogue records. Firstly, we learn the relationship information between users, goods and attributes in comments and dialogue records through graph neural network, so as to ensure that the system can ask the most relevant questions related to user preferences. Secondly, the improved transformer is used to model the multi type behavior sequence of users to learn the potential interests of users. Finally, it is fused with the learned relationship information to make recommendations. The experimental results on a multi domain dialogue data set show that the proposed model can obtain higher accuracy with less dialogue times.
关键词
对话推荐 /
行为序列 /
知识图 /
自注意力机制
{{custom_keyword}} /
Key words
conversational recommendation /
behavior sequence /
knowledge graph /
self-attention mechanism
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] SUN Y, ZHANG Y. Conversational recommender system[C]//Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, 2018: 235-244.
[2] ZHANG Y, CHEN X, AI Q,et al.Towards conversational search and recommendation: System ask, user respond[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 2018: 177-186.
[3] GUAN X, TSUN C, GUAN Y. Active learning in multi-domain collaborative filtering recommender systems[C]//Proceedings of the 33rd Annual ACM Symposium on Applied Computing, 2018: 1351-1357.
[4] RENDLE S,FREUDENTHALER C,GANTNER Z, et al. BPR: Bayesian personalized ranking from implicit feedback[C]//Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence,2009:452-461.
[5] BILIH P. Preference elicitation strategy for conversational recommender system[C]//Proceedings of the 12th ACM International Conference on Web Search and Data Mining, 2019: 824-825.
[6] HOYEOP L, JINBAE I, SEONGWON J, et al. MeLU: meta-learned user preference estimator for coldstart recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019: 1073-1082.
[7] MA J, ZHOU C, CUI P,et al. Learning disentangled representations for recommendation[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems, 2019: 5711-5722.
[8] GAO C, LEI L, HE X, et al. Advances and challenges in conversational recommender systems: A survey[J].AI Open, 2021(2): 100-126.
[9] TAN Y, XU X, LIU Y. Improved recurrent neural networks for session-based recommendations[C]//Proceedings of the 1st Workshop on Deep Learning for Recommender Systems,2016: 17-22.
[10] YOU J, WANG Y, ADITYA P, et al. Hierarchical temporal convolutional networks for dynamic recommender systems[C]//Proceedings of International Conference on World Wide Web, 2019: 2236-2246.
[11] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of Advances in Neural Information Processing Systems, 2017: 5998-6008.
[12] LI J, REN P, CHEN Z,et al. Neural attentive session-based recommendation[C]//Proceedings of International Conference on Information and Knowledge Management,2017: 1419-1428.
[13] LIU Q, ZENG Y, REFUOE M, et al. STAMP: Short-Term attention/memory priority model for session-based recommendation[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018: 1831-1839.
[14] LI J, WANG Y, JULIAN J. Time interval aware self-attention for sequential recommendation[C]//Proceedings of the 13th International Conference on Web Search and Data Mining,2020: 322-330.
[15] HUANG J, ZHAO W, DOU H,et al. Improving sequential recommendation with knowledge-enhanced memory networks[C]//Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, 2018: 505-514.
[16] HE X, DENG K, WANG X, et al.LightGCN: Simplifying and powering graph convolution network for recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020: 639-648.
[17] MICHAEL S, THOMAS N, PETER B,et al. Modeling relational data with graph convolutional networks[C]//Proceedings of European Semantic Web Conference, 2018: 593-607.
[18] WANG X, HE X, WANG M, et al.Neural graph collaborative filtering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019: 165-174.
[19] MOON S, PARARTH S, ANUJ K, et al. Opendialkg: Explainable conversational reasoning with attention-based walks over knowledge graphs[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019: 845-854.
[20] CHEN Q, LIN J, ZHANG Y, et al. Towards knowledge-based recommender dialog system[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing,2019: 1803-1813.
[21] RAYMOND L, SAMIRA E, HANNES S,et al. Towards deep conversational recommendations[C]//Proceedings of the Advances in Neural Information Processing Systems, 2018: 9725-9735.
[22] ZOU J, CHEN Y, KANOULAS E. Towards question-based recommender systems[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020: 881-890.
[23] ALI M, JAMES A, PHILIP S. Large-scale interactive conversational recommendation system using actor-critic framework[C]//Proceedings of the 15th ACM Conference on Recommender Systems, 2021: 220-229.
[24] MA W, TAKANOBU R, HUANG M. CR-Walker: Tree-structured graph reasoning and dialog acts for conversational recommendation[C]//Proceedings of the Empirical Methods in Natural Language Processing, 2021: 1839-1851.
[25] NI J, LI J, JULIAN M. Justifying recommendations using distantly-labeled reviews and fined-grained aspects [C]//Proceedings of the Empirical Methods in Natural Language Processing, 2019: 188-197.
[26] FU Z, XIAN Y, ZHU Y, et al. COOKIE: A dataset for conversational recommendation over knowledge graphs in e-commerce[C]//Proceedings of the 43th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020: 2415-2421.
[27] GU J, LU Z, LI H, et al. Incorporating copying mechanism in sequence-to-sequence learning[C]//Proceedings of the 54th annual meeting of the association for computational linguistics, 2016: 1631-1640.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61775139)
{{custom_fund}}
PDF(5470 KB)
