Personalized Search Via Neural Contextual Semantic Relevance Ranking

TL;DR

This paper introduces a neural framework for personalized search ranking that incorporates user context and query semantics to improve relevance and adapt results to individual preferences.

Contribution

It proposes a novel neural learning approach that models document-query relationships using lexical and semantic features for personalized search.

Findings

Significant improvement in search relevance metrics

Effective modeling of user context enhances personalization

Validated on real-world search dataset

Abstract

Existing neural relevance models do not give enough consideration for query and item context information which diversifies the search results to adapt for personal preference. To bridge this gap, this paper presents a neural learning framework to personalize document ranking results by leveraging the signals to capture how the document fits into users' context. In particular, it models the relationships between document content and user query context using both lexical representations and semantic embeddings such that the user's intent can be better understood by data enrichment of personalized query context information. Extensive experiments performed on the search dataset, demonstrate the effectiveness of the proposed method.