Contrastive Learning of User Behavior Sequence for Context-Aware Document Ranking
This work addresses the challenge of variable user behavior in search sessions for improving document ranking, representing an incremental advance over existing methods.
The paper tackled the problem of learning robust user behavior sequences for context-aware document ranking by proposing a contrastive learning method with data augmentation to handle variations in user queries and clicks, resulting in significant outperformance over state-of-the-art methods on two real query log datasets.
Context information in search sessions has proven to be useful for capturing user search intent. Existing studies explored user behavior sequences in sessions in different ways to enhance query suggestion or document ranking. However, a user behavior sequence has often been viewed as a definite and exact signal reflecting a user's behavior. In reality, it is highly variable: user's queries for the same intent can vary, and different documents can be clicked. To learn a more robust representation of the user behavior sequence, we propose a method based on contrastive learning, which takes into account the possible variations in user's behavior sequences. Specifically, we propose three data augmentation strategies to generate similar variants of user behavior sequences and contrast them with other sequences. In so doing, the model is forced to be more robust regarding the possible variations. The optimized sequence representation is incorporated into document ranking. Experiments on two real query log datasets show that our proposed model outperforms the state-of-the-art methods significantly, which demonstrates the effectiveness of our method for context-aware document ranking.