Personalized Transformer for Explainable Recommendation
This addresses the need for personalized natural language generation in recommendation systems, offering a unified model for both recommendation and explanation, though it is incremental as it builds on existing Transformer architectures.
The paper tackled the problem of personalizing Transformer models for explainable recommendation by introducing PETER, which uses user and item IDs to predict words in explanations, resulting in a model that outperforms fine-tuned BERT in effectiveness and efficiency.
Personalization of natural language generation plays a vital role in a large spectrum of tasks, such as explainable recommendation, review summarization and dialog systems. In these tasks, user and item IDs are important identifiers for personalization. Transformer, which is demonstrated with strong language modeling capability, however, is not personalized and fails to make use of the user and item IDs since the ID tokens are not even in the same semantic space as the words. To address this problem, we present a PErsonalized Transformer for Explainable Recommendation (PETER), on which we design a simple and effective learning objective that utilizes the IDs to predict the words in the target explanation, so as to endow the IDs with linguistic meanings and to achieve personalized Transformer. Besides generating explanations, PETER can also make recommendations, which makes it a unified model for the whole recommendation-explanation pipeline. Extensive experiments show that our small unpretrained model outperforms fine-tuned BERT on the generation task, in terms of both effectiveness and efficiency, which highlights the importance and the nice utility of our design.