Conversational Recommender Systems based on Topic Prediction and Retrieval
Authors: 
Xiaofeng Cui, Liang LiAuthors Info & Claims
Xiaofeng Cui, Liang LiAuthors Info & ClaimsPages 466 - 471
Abstract
The goal of conversation recommendation systems is to provide users with high-quality, personalized responses by analyzing conversation history, understanding user intent and context, and utilizing relevant knowledge and data. Existing conversation recommendation systems based on prompt learning, which generate response templates from fused knowledge representations generated by pre-trained semantic fusion modules, task-specific soft tokens and conversation contexts, utilize response templates generated from conversation sub-tasks as an important part of the prompts to enhance the recommendation subtask. However, the prompt information in existing methods is limited and may not fit well with the recommendation results when generating the final conversation. To this end, this article proposes a method, TPRCRS (Conversational Recommender Systems based on Topic Prediction and Retrieval), which predicts topics through the conversation context, the previous round of conversation topics, and the behavior of users and systems. Subsequently, through conversation topics, vocabulary, entities and semantic fusion and pre-training, using the fused topics to search in the datasets. When a result is found, it is treated as a conversation template and applied to the recommendation task; otherwise, the prompt is used to generate a conversation template. Finally, the optimal reply is generated through a hint learning method. Experiments show that TPRCRS achieves significantly improved results in two tasks.
References
[1]
Roy D, Dutta M. A systematic review and research perspective on recommender systems[J]. Journal of Big Data, 2022, 9(1): 59.
[2]
Ko H, Lee S, Park Y, A survey of recommendation systems: recommendation models, techniques, and application fields[J]. Electronics, 2022, 11(1): 141.
[3]
Li R, Ebrahimi Kahou S, Schulz H, Towards deep conversational recommendations[J]. Advances in neural information processing systems, 2018, 31.
[4]
Gao C, Lei W, He X, Advances and challenges in conversational recommender systems: A survey[J]. AI Open, 2021, 2: 100-126.
[5]
Jannach D, Manzoor A, Cai W, A survey on conversational recommender systems[J]. ACM Computing Surveys (CSUR), 2021, 54(5): 1-36.
[6]
Chen Q, Lin J, Zhang Y, Towards knowledge-based recommender dialog system[J]. arXiv preprint arXiv:1908.05391, 2019.
[7]
Zhou K, Zhao W X, Bian S, Improving conversational recommender systems via knowledge graph based semantic fusion[C]//Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. 2020: 1006-1014.
[8]
Li S, Lei W, Wu Q, Seamlessly unifying attributes and items: Conversational recommendation for cold-start users[J]. ACM Transactions on Information Systems (TOIS), 2021, 39(4): 1-29.
[9]
Wang X, Zhou K, Wen J R, Towards unified conversational recommender systems via knowledge-enhanced prompt learning[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2022: 1929-1937.
[10]
Brown T, Mann B, Ryder N, Language models are few-shot learners[J]. Advances in neural information processing systems, 2020, 33: 1877-1901.
[11]
Gao T, Fisch A, Chen D. Making pre-trained language models better few-shot learners[J]. arXiv preprint arXiv:2012.15723, 2020.
[12]
Wang L, Hu H, Sha L, Finetuning large-scale pre-trained language models for conversational recommendation with knowledge graph[J]. arXiv preprint arXiv:2110.07477, 2021.
[13]
Jiang Z, Xu F F, Araki J, How can we know what language models know?[J]. Transactions of the Association for Computational Linguistics, 2020, 8: 423-438.
[14]
Xing C, Wu W, Wu Y, Topic aware neural response generation[C]//Proceedings of the AAAI conference on artificial intelligence. 2017, 31(1).
[15]
Lian R, Xie M, Wang F,et al.Learning to Select Knowledge for Response Generation in Dialog Systems[J]. 2019.
[16]
Tang J, Zhao T, Xiong C, Target-guided open-domain conversation[J]. arXiv preprint arXiv:1905.11553, 2019.
[17]
Xu J, Wang H, Niu Z Y, Conversational graph grounded policy learning for open-domain conversation generation[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020: 1835-1845.
[18]
Manzoor A, Jannach D. Towards retrieval-based conversational recommendation[J]. Information Systems, 2022, 109: 102083.
[19]
Manzoor A, Jannach D. Generation-based vs. retrieval-based conversational recommendation: A user-centric comparison[C]//Proceedings of the 15th ACM Conference on Recommender Systems. 2021: 515-520.
[20]
Zhang Y, Sun S, Galley M, Dialogpt: Large-scale generative pre-training for conversational response generation[J]. arXiv preprint arXiv:1911.00536, 2019.
[21]
Zhou K, Zhou Y, Zhao W X, Towards topic-guided conversational recommender system[J]. arXiv preprint arXiv:2010.04125, 2020.
[22]
Liu Y, Ott M, Goyal N, Roberta: A robustly optimized bert pretraining approach[J]. arXiv preprint arXiv:1907.11692, 2019.
[23]
Hayati S A, Kang D, Zhu Q, Inspired: Toward sociable recommendation dialog systems[J]. arXiv preprint arXiv:2009.14306, 2020.
[24]
Subramanian S, Trischler A, Bengio Y, Learning general purpose distributed sentence representations via large scale multi-task learning[J]. arXiv preprint arXiv:1804.00079, 2018.
[25]
He X, Liao L, Zhang H, Neural collaborative filtering[C]//Proceedings of the 26th international conference on world wide web. 2017: 173-182.
[26]
Vaswani A, Shazeer N, Parmar N, Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.
[27]
Zhang T, Liu Y, Zhong P, Kecrs: Towards knowledge-enriched conversational recommendation system[J]. arXiv preprint arXiv:2105.08261, 2021.
[28]
Yu T, Shen Y, Jin H. Towards hands-free visual dialog interactive recommendation[C]//Proceedings of the AAAI conference on artificial intelligence. 2020, 34(01): 1137-1144.
Index Terms
- Conversational Recommender Systems based on Topic Prediction and Retrieval
Recommendations
Customized Conversational Recommender Systems
Machine Learning and Knowledge Discovery in DatabasesAbstractConversational recommender systems (CRS) aim to capture user’s current intentions and provide recommendations through real-time multi-turn conversational interactions. As a human-machine interactive system, it is essential for CRS to improve the ...
Unifying Recommender Systems and Conversational User Interfaces
CUI '22: Proceedings of the 4th Conference on Conversational User InterfacesThis paper considers unifying research on conversational user interfaces and recommender systems. Studies on conversational user interfaces (CUIs) typically examine how conversations can be facilitated (i.e., optimizing the means). Recommender systems ...
Linguistics-based dialogue simulations to evaluate argumentative conversational recommender systems
AbstractConversational recommender systems aim at recommending the most relevant information for users based on textual or spoken dialogues, through which users can communicate their preferences to the system more efficiently. Argumentative conversational ...
Comments
Information & Contributors
Information
Published In
December 2023
1132 pages
ISBN:9798400716157
DOI:10.1145/3660043
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 30 May 2024
Check for updates
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICIEAI 2023
ICIEAI 2023: 2023 International Conference on Information Education and Artificial Intelligence
December 22 - 24, 2023
Xiamen, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 46Total Downloads
- Downloads (Last 12 months)46
- Downloads (Last 6 weeks)14
Reflects downloads up to 01 Mar 2025
Other Metrics
Citations
View Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML FormatLogin options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in