论文标题
在基于BERT的会话感知顺序建议中利用会话信息
Exploiting Session Information in BERT-based Session-aware Sequential Recommendation
论文作者
论文摘要
在推荐系统中，利用用户互动历史记录作为顺序信息，可以改善性能。但是，在许多在线服务中，用户交互通常由大概共享偏好的会话分组，这与普通序列表示技术需要不同的方法。为此，已经开发了具有层次结构或各种观点的序列表示模型，但具有相当复杂的网络结构。在本文中，我们提出了三种方法，通过利用会话信息来提高建议性能，同时最大程度地减少基于BERT的顺序建议模型中的其他参数：使用会话令牌，添加会话段嵌入式以及时间认识的自我注意力。我们通过广泛使用的建议数据集实验证明了提出方法的可行性。
In recommendation systems, utilizing the user interaction history as sequential information has resulted in great performance improvement. However, in many online services, user interactions are commonly grouped by sessions that presumably share preferences, which requires a different approach from ordinary sequence representation techniques. To this end, sequence representation models with a hierarchical structure or various viewpoints have been developed but with a rather complex network structure. In this paper, we propose three methods to improve recommendation performance by exploiting session information while minimizing additional parameters in a BERT-based sequential recommendation model: using session tokens, adding session segment embeddings, and a time-aware self-attention. We demonstrate the feasibility of the proposed methods through experiments on widely used recommendation datasets.
