Enhancing Potential Re-Finding in Personalized Search With Hierarchical Memory Networks

• Published in: IEEE transactions on knowledge and data engineering Vol. 35; no. 4; pp. 3846 - 3857
• Main Authors: Zhou, Yujia, Dou, Zhicheng, Wen, Ji-Rong
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Behavior; Computational modeling; Customization; Deep learning; Documents; Feature extraction; hierarchical memory networks; History; Networks; Personalized search; Queries; re-finding identification; Search engines; Search problems; Searching; Semantics
• ISSN: 1041-4347; 1558-2191
• DOI: 10.1109/TKDE.2021.3126066

The goal of personalized search is to tailor the document ranking list to meet user's individual needs. Previous studies showed users usually look for the information that has been searched before. This is called re-finding behavior which is widely explored in existing personalized search approaches. However, most existing methods for identifying re-finding behavior focus on simple lexical similarities between queries. In this paper, we propose a personalized framework based on hierarchical memory networks (MN) to enhance the identification of the potential re-finding behavior. Specifically, we explore the potential re-finding behaviors of users from two dimensions. (1) Granularity dimension. The framework carries out re-finding identification with external memories from word, sentence, and session levels. (2) Query intent dimension. Query-based re-finding and document-based re-finding are taken into account to cover user's different query intents. To enhance the interaction between different memory slots, we optimize the <inline-formula><tex-math notation="LaTeX">READ</tex-math> <mml:math><mml:mrow><mml:mi>R</mml:mi><mml:mi>E</mml:mi><mml:mi>A</mml:mi><mml:mi>D</mml:mi></mml:mrow></mml:math><inline-graphic xlink:href="zhou-ieq1-3126066.gif"/> </inline-formula> operation of MN with two strategies that utilize the information in memory in a multi-hop way. Endowed with these memory networks, we can enhance user's potential re-finding behaviors and build a fine-grained user model dynamically. Experimental results on two datasets have a significant improvement over baselines, and the optimized <inline-formula><tex-math notation="LaTeX">READ</tex-math> <mml:math><mml:mrow><mml:mi>R</mml:mi><mml:mi>E</mml:mi><mml:mi>A</mml:mi><mml:mi>D</mml:mi></mml:mrow></mml:math><inline-graphic xlink:href="zhou-ieq2-3126066.gif"/> </inline-formula> operation shows better performance.