Bridge the Gap between Past and Future: Siamese Model Optimization for Context-Aware Document Ranking

TL;DR

This paper introduces a novel siamese model framework that integrates future user behavior predictions with historical session data to improve document ranking in information retrieval, addressing the challenge of evolving user intent.

Contribution

It proposes a collaborative training framework with a history-conditioned and a future-aware model, utilizing peer knowledge distillation and dynamic gating for enhanced ranking performance.

Findings

ForeRanker outperforms existing methods on benchmark datasets.

The approach effectively captures evolving user intent.

Peer knowledge distillation improves model consistency.

Abstract

In the realm of information retrieval, users often engage in multi-turn interactions with search engines to acquire information, leading to the formation of sequences of user feedback behaviors. Leveraging the session context has proven to be beneficial for inferring user search intent and document ranking. A multitude of approaches have been proposed to exploit in-session context for improved document ranking. Despite these advances, the limitation of historical session data for capturing evolving user intent remains a challenge. In this work, we explore the integration of future contextual information into the session context to enhance document ranking. We present the siamese model optimization framework, comprising a history-conditioned model and a future-aware model. The former processes only the historical behavior sequence, while the latter integrates both historical and anticipated future behaviors. Both models are trained collaboratively using the supervised labels and pseudo labels predicted by the other. The history-conditioned model, referred to as ForeRanker, progressively learns future-relevant information to enhance ranking, while it singly uses historical session at inference time. To mitigate inconsistencies during training, we introduce the peer knowledge distillation method with a dynamic gating mechanism, allowing models to selectively incorporate contextual information. Experimental results on benchmark datasets demonstrate the effectiveness of our ForeRanker, showcasing its superior performance compared to existing methods.