Converse-Et-Impera: Exploiting Deep Learning and Hierarchical Reinforcement Learning for Conversational Recommender Systems

Greco, Claudio; Suglia, Alessandro; Basile, Pierpaolo; Semeraro, Giovanni

doi:10.1007/978-3-319-70169-1_28

Cited by 28 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reinforcement learning and deep learning on dialogue agents have also been studied for recommendations [4,6,11,20,22]. Sun and Zhang [34] proposed a deep reinforcement learning framework to build a conversational recommendation agent, which queries users on item facets and focuses on the long-term utility of success or conversion rate.…”

Section: Recommendation Modulementioning

confidence: 99%

Towards Question-based Recommender Systems

Zou

Chen

Kanoulas

2020

Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Conversational and question-based recommender systems have gained increasing attention in recent years, with users enabled to converse with the system and better control recommendations. Nevertheless, research in the field is still limited, compared to traditional recommender systems. In this work, we propose a novel Question-based recommendation method, Qrec, to assist users to find items interactively, by answering automatically constructed and algorithmically chosen questions. Previous conversational recommender systems ask users to express their preferences over items or item facets. Our model, instead, asks users to express their preferences over descriptive item features. The model is first trained offline by a novel matrix factorization algorithm, and then iteratively updates the user and item latent factors online by a closed-form solution based on the user answers. Meanwhile, our model infers the underlying user belief and preferences over items to learn an optimal question-asking strategy by using Generalized Binary Search, so as to ask a sequence of questions to the user. Our experimental results demonstrate that our proposed matrix factorization model outperforms the traditional Probabilistic Matrix Factorization model. Further, our proposed Qrec model can greatly improve the performance of state-of-the-art baselines, and it is also effective in the case of cold-start user and item recommendations.

show abstract

Section: Recommendation Modulementioning

confidence: 99%

Towards Question-based Recommender Systems

Zou

Chen

Kanoulas

2020

Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

show abstract

“…On the other hand, approaches that are entirely based on natural language interactions include, for example, task-oriented dialogue systems like the early proposal from [121], the explanationaware conversational system proposed in [104], as well as more recent (deep) learning-based approaches, e.g., [45,47,75]. Spoken-text-only approaches are often implemented on smart speakers like Amazon Alexa or Google Home, e.g., [4,36].…”

Section: Input and Output Modalitiesmentioning

confidence: 99%

A Survey on Conversational Recommender Systems

Jannach,

Manzoor,

Cai

et al. 2020

Preprint

View full text Add to dashboard Cite

Recommender systems are software applications that help users to find items of interest in situations of information overload. Current research often assumes a one-shot interaction paradigm, where the users' preferences are estimated based on past observed behavior and where the presentation of a ranked list of suggestions is the main, one-directional form of user interaction. Conversational recommender systems (CRS) take a different approach and support a richer set of interactions. These interactions can, for example, help to improve the preference elicitation process or allow the user to ask questions about the recommendations and to give feedback. The interest in CRS has significantly increased in the past few years. This development is mainly due to the significant progress in the area of natural language processing, the emergence of new voice-controlled home assistants, and the increased use of chatbot technology. With this paper, we provide a detailed survey of existing approaches to conversational recommendation. We categorize these approaches in various dimensions, e.g., in terms of the supported user intents or the knowledge they use in the background. Moreover, we discuss technological approaches, review how CRS are evaluated, and finally identify a number of gaps that deserve more research in the future. CCS Concepts: • Information systems → Recommender systems; • General and reference → Surveys and overviews; • Human-centered computing → Interactive systems and tools;

show abstract

“…Multimodal data, such as natural language and image, have been leveraged in recommender systems. With the recent advances of deep learning and reinforcement learning, conversational interactive recommendations are becoming increasingly popular (Christakopoulou, Radlinski, and Hofmann 2016;Greco et al 2017;Sun and Zhang 2018;Li et al 2018;Zhang et al 2018). A recent work (Guo et al 2018) enables user natural language feedback to candidate items' visual appearance for interactive item retrieval.…”

Section: Related Work Interactive Recommenders With Multimodal Datamentioning

confidence: 99%

Towards Hands-Free Visual Dialog Interactive Recommendation

Shen

Jin

2020

AAAI

View full text Add to dashboard Cite

With the recent advances of multimodal interactive recommendations, the users are able to express their preference by natural language feedback to the item images, to find the desired items. However, the existing systems either retrieve only one item or require the user to specify (e.g., by click or touch) the commented items from a list of recommendations in each user interaction. As a result, the users are not hands-free and the recommendations may be impractical. We propose a hands-free visual dialog recommender system to interactively recommend a list of items. At each time, the system shows a list of items with visual appearance. The user can comment on the list in natural language, to describe the desired features they further want. With these multimodal data, the system chooses another list of items to recommend. To understand the user preference from these multimodal data, we develop neural network models which identify the described items among the list and further predict the desired attributes. To achieve efficient interactive recommendations, we leverage the inferred user preference and further develop a novel bandit algorithm. Specifically, to avoid the system exploring more than needed, the desired attributes are utilized to reduce the exploration space. More importantly, to achieve sample efficient learning in this hands-free setting, we derive additional samples from the user's relative preference expressed in natural language and design a pairwise logistic loss in bandit learning. Our bandit model is jointly updated by the pairwise logistic loss on the additional samples derived from natural language feedback and the traditional logistic loss. The empirical results show that the probability of finding the desired items by our system is about 3 times as high as that by the traditional interactive recommenders, after a few user interactions.

show abstract

Converse-Et-Impera: Exploiting Deep Learning and Hierarchical Reinforcement Learning for Conversational Recommender Systems

Cited by 28 publications

References 16 publications

Towards Question-based Recommender Systems

Towards Question-based Recommender Systems

A Survey on Conversational Recommender Systems

Towards Hands-Free Visual Dialog Interactive Recommendation

Contact Info

Product

Resources

About