PSSL: Self-supervised Learning for Personalized Search with Contrastive Sampling
This addresses data sparsity for personalized search systems, though it is incremental as it builds on existing methods with self-supervised enhancements.
The paper tackles data sparsity and poor generalizability in neural personalized search by proposing PSSL, a framework using self-supervised learning with contrastive sampling, which achieves state-of-the-art performance on two datasets.
Personalized search plays a crucial role in improving user search experience owing to its ability to build user profiles based on historical behaviors. Previous studies have made great progress in extracting personal signals from the query log and learning user representations. However, neural personalized search is extremely dependent on sufficient data to train the user model. Data sparsity is an inevitable challenge for existing methods to learn high-quality user representations. Moreover, the overemphasis on final ranking quality leads to rough data representations and impairs the generalizability of the model. To tackle these issues, we propose a Personalized Search framework with Self-supervised Learning (PSSL) to enhance data representations. Specifically, we adopt a contrastive sampling method to extract paired self-supervised information from sequences of user behaviors in query logs. Four auxiliary tasks are designed to pre-train the sentence encoder and the sequence encoder used in the ranking model. They are optimized by contrastive loss which aims to close the distance between similar user sequences, queries, and documents. Experimental results on two datasets demonstrate that our proposed model PSSL achieves state-of-the-art performance compared with existing baselines.