Enhancing Potential Re-Finding in Personalized Search With Hierarchical Memory Networks
- 9 November 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (4) , 3846-3857
Abstract
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 $READ$ 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 $READ$ operation shows better performance.
Keywords
Funding Information
- National Natural Science Foundation of China (61872370, 61832017)
- Beijing Outstanding Young Scientist Program (BJJWZYJH012019100020098)
- China Unicom Innovation Ecological Cooperation Plan
- Intelligent Social Governance Platform
- Major Innovation & Planning Interdisciplinary Platform for the Double-First Class Initiative
- Renmin University of China
This publication has 30 references indexed in Scilit:
- Temporal Latent Topic User Profiles for Search Personalisation2015
- Improving search personalisation with dynamic group formation2014
- Personalized document re-ranking based on Bayesian probabilistic matrix factorization2014
- Adapting deep RankNet for personalized search2014
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Enhancing personalized search by mining and modeling task behavior2013
- Modeling and analysis of cross-session search tasks2011
- The Probabilistic Relevance Framework: BM25 and BeyondFoundations and Trends® in Information Retrieval, 2009
- A large-scale evaluation and analysis of personalized search strategies2007
- Investigating behavioral variability in web search2007