UCRI: A Unified Conversational Recommender System Based on Item-Guided Conditional Generation

In recent years, great efforts have been made to develop the conversational recommender system (CRS). However, existing works always ignore the incorporation of the recommended items and the generated replies. This causes the performance of the recommendation degrading in the conversations. To solve this problem, we propose a novel framework called UCRI to fuse the recommender module and the dialogue module seamlessly. UCRI captures the semantic similarity between the recommended items and the candidate words to realize the item-guided conditional generation. Besides, we further design the weight control mechanism and the recommender gating mechanism to make accurate recommendations in the conversations. Our approach can explicitly generate the recommended items in the replies and encourage the model to generate the related context for the items. Extensive experiments on the benchmark dataset REDIAL show that our model achieves the best performance on both item recommendation and reply generation tasks.