Dual Learning for Explainable Recommendation: Towards Unifying User Preference Prediction and Review Generation

Sun, Peijie; Wu, Le; Zhang, Kun; Fu, Yanjie; Hong, Richang; Wang, Meng

doi:10.1145/3366423.3380164

Cited by 81 publications

(36 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, TIM [23] models users and items within the topic space which is learned from the review data. Another direction of this field is to provide explanations for item recommendations based on text reviews [24], [25], [26]. Different from the above works which mainly focus on tackle rating prediction tasks or ranking tasks with text reviews, we focus on distinguishing user intentions from reviews so as to construct user-specific re-ranking model.…”

Section: Related Workmentioning

confidence: 99%

Attention over Self-attention:Intention-aware Re-ranking with Dynamic Transformer Encoders for Recommendation

Lin¹,

Zang²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Re-ranking models refine the item recommendation list generated by the prior global ranking model with intra-item relationships. However, most existing re-ranking solutions refine recommendation list based on the implicit feedback with a shared re-ranking model, which regrettably ignore the intra-item relationships under diverse user intentions. In this paper, we propose a novel Intention-aware Re-ranking Model with Dynamic Transformer Encoder (RAISE), aiming to perform user-specific prediction for each target user based on her intentions. Specifically, we first propose to mine latent user intentions from text reviews with an intention discovering module (IDM). By differentiating the importance of review information with a co-attention network, the latent user intention can be explicitly modeled for each user-item pair. We then introduce a dynamic transformer encoder (DTE) to capture user-specific intra-item relationships among item candidates by seamlessly accommodating the learnt latent user intentions via IDM. As such, RAISE is able to perform user-specific prediction without increasing the depth (number of blocks) and width (number of heads) of the prediction model. Empirical study on four public datasets shows the superiority of our proposed RAISE, with up to 13.95%, 12.30%, and 13.03% relative improvements evaluated by Precision, MAP, and NDCG respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Attention over Self-attention:Intention-aware Re-ranking with Dynamic Transformer Encoders for Recommendation

Lin¹,

Zang²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…• AMCF [38]. This method also adds the item's attributes into the matrix factorization by enriching the item representation with the attribute representation.…”

Section: Experimental Settingsmentioning

confidence: 99%

Dual Preference Distribution Learning for Item Recommendation

Duan¹,

Song²,

Zheng³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recommender systems can automatically recommend users items that they probably like, for which the goal is to represent the user and item as well as model their interaction. Existing methods have primarily learned the user's preferences and item's features with vectorized representations, and modeled the user-item interaction by the similarity of their representations. In fact, the user's different preferences are related and capturing such relations could better understand the user's preferences for a better recommendation. Toward this end, we propose to represent the user's preference with multi-variant Gaussian distribution, and model the user-item interaction by calculating the probability density at the item in the user's preference distribution. In this manner, the mean vector of the Gaussian distribution is able to capture the center of the user's preferences, while its covariance matrix captures the relations of these preferences. In particular, in this work, we propose a dual preference distribution learning framework (DUPLE), which captures the user's preferences to both the items and attributes by a Gaussian distribution, respectively. As a byproduct, identifying the user's preference to specific attributes enables us to provide the explanation of recommending an item to the user. Extensive quantitative and qualitative experiments on six public datasets show that DUPLE achieves the best performance over all state-of-the-art recommendation methods.

show abstract

“…Self-supervised learning aims at supervising a network via an objective where the ground-truth labels are automatically obtained from the raw data itself [26] It benefits a range of tasks, such as pre-trained models [7,19], recommender systems [40,41,50,52,67], summarization [48] and open-domain conversational agents [51,55,56,60]. The application in the last task is closest to our work.…”

Section: Self-supervised Learningmentioning

confidence: 99%

Initiative-Aware Self-Supervised Learning for Knowledge-Grounded Conversations

Chen

Ren

Chen

et al. 2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

In the knowledge-grounded conversation (KGC) task systems aim to produce more informative responses by leveraging external knowledge. KGC includes a vital part, knowledge selection, where conversational agents select the appropriate knowledge to be incorporated in the next response. Mixed initiative is an intrinsic feature of conversations where the user and the system can both take the initiative in suggesting new conversational directions. Knowledge selection can be driven by the user's initiative or by the system's initiative. For the former, the system usually selects knowledge according to the current user utterance that contains new topics or questions posed by the user; for the latter, the system usually selects knowledge according to the previously selected knowledge. No previous study has considered the mixed-initiative characteristics of knowledge selection to improve its performance.In this paper, we propose a mixed-initiative knowledge selection method (MIKe) for KGC, which explicitly distinguishes between user-initiative and system-initiative knowledge selection. Specifically, we introduce two knowledge selectors to model both of them separately, and design a novel initiative discriminator to discriminate the initiative type of knowledge selection at each conversational turn. A challenge for training MIKe is that we usually have no labels for indicating initiative. To tackle this challenge, we devise an initiative-aware self-supervised learning scheme that helps MIKe to learn to discriminate the initiative type via a self-supervised task. Experimental results on two datasets show that MIKe significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, indicating that it can select more appropriate knowledge and generate more informative and engaging responses.

show abstract

Dual Learning for Explainable Recommendation: Towards Unifying User Preference Prediction and Review Generation

Cited by 81 publications

References 24 publications

Attention over Self-attention:Intention-aware Re-ranking with Dynamic Transformer Encoders for Recommendation

Attention over Self-attention:Intention-aware Re-ranking with Dynamic Transformer Encoders for Recommendation

Dual Preference Distribution Learning for Item Recommendation

Initiative-Aware Self-Supervised Learning for Knowledge-Grounded Conversations

Contact Info

Product

Resources

About