Soliciting User Preferences in Conversational Recommender Systems via Usage-related Questions

Abstract

Conversational Recommender Systems are recommender systems that utilize multi-turn interactions in order to help users find items of interest. Their advantage over traditional, one-shot recommender systems lies in their ability to elicit and adapt to the changing user preference in real time.Common approaches to eliciting user preferences include asking about items and item attributes. This strategies can fail, if the user does not have the prerequisite knowledge about the item or item attributes but they know what they plan to use the item for. In this thesis we propose a novel approach to eliciting preferences by asking implicit questions based on item usage.We identify the sentences form a large corpora of user reviews that contain information about item usage. Based on those sentences and by utilizing crowd workers, we generate questions that could be used in an preference elicitation setting. Lastly, based on the labelled dataset, we train a large neural model to automatically generate question for any viable sentence in the corpus.Using standard metrics for automatic evaluations of generated questions and manual evaluation, we demonstrate the potential viability of such a system in a production setting.Finally, we identify clusters of questions where the system fails. i Thank you to the University of Stavanger for the great years of studying, for giving me the opportunity to do this research and for the access to essential hardware.Thank you Krisztian Balog for being my mentor and a great teacher. Thank you for your contribution in bringing forward this idea and for continuous invaluable guidance throughout the project. Our weekly meetings gave me inspiration and motivation to keep working and expanding the scope of the research.Thank you Filip Radlinski also for being my mentor, supporting the idea and providing great insights and new ideas.Thank you to my girlfriend Kirsti for unwavering support through my years of study, and especially these last couple of months while working with this thesis.Thank you to my daughter Matilde, born just after we started this project. While giving me some sleepless nights and countless of distractions, you bring joy to my every day, even when I am stressed or tired.

Supporting Complex Information-Seeking Tasks with Implicit Constraints

“…The models proposed in this paper are unique in modeling the user intent, and they can be baselines for future research in this area, since the current conversational and exploratory search models [51,64,85] are not applicable to tackle the described task. For convenience, we Algorithm 3 Algorithm to generate corpus for evaluation.…”

“…Recent advances in the field of Natural Language Understanding (NLU) [1,14,28] have enabled natural language interfaces to help users find information beyond what typical search engines provide, through systems such as open domain and task-oriented dialogue engines [58,59] and conversational recommenders [19], among others. However, most existing systems still present with one or both of the following limitations: (1) answers are typically constrained to relatively simple and primarily factoid-style requests in natural language [54,81], as is the case with search engines; and (2) a requirement on availability of inferred user preferences [51].…”

Explainable Active Learning for Preference Elicitation

“…In the case of literally no user data, an initial preference elicitation step is carried out with interactive recommendation approaches. These approaches can apply several channels for the acquisition of user knowledge, such as demographic filtering (Adomavicius & Tuzhilin, 2005), presenting a set of features or contexts to be selected (Druck, Settles, & McCallum, 2009;Khan, Smyth, & Coyle, 2021), providing a set of example recommendations to be labeled (Pecune, Callebert, & Marsella, 2020), and question-based preference elicitation (Buzcu et al, 2022;Kostric, Balog, & Radlinski, 2021) or intent detection via intelligent dialogue systems (Liu, Li, & Lin, 2019). An initial interaction phase with the user supply data that enable the execution of subsequent recommendation models.…”

Evaluating conversational recommender systems

“…Such considerations can be implemented both in traditional interactive sales advisory solutions (Widyantoro and Baizal 2014;Jannach 2004), but also in modern approaches based on machine learning. In a recent work Kostric et al (2021) present a promising approach for generating what they call implicit questions, which may help advance natural-language based systems beyond today's predominant slot-filling approaches. Furthermore, Radlinski et al (2022) investigate challenges of understanding and modeling subjective attributes to overcome limitations of traditional slot-filling techniques.…”