TPRM: A Topic-based Personalized Ranking Model for Web Search
Minghui Huang, Wei Peng, Dong Wang

TL;DR
This paper introduces TPRM, a novel topic-based personalized ranking model that combines user profiles with contextualized term representations to improve web search relevance.
Contribution
The paper presents a new personalized ranking model that effectively integrates user topical profiles with pretrained language models for enhanced search results.
Findings
TPRM outperforms existing ad-hoc and personalized ranking models.
Experimental results demonstrate significant improvements in ranking accuracy.
The model effectively leverages user profiles and semantic representations.
Abstract
Ranking models have achieved promising results, but it remains challenging to design personalized ranking systems to leverage user profiles and semantic representations between queries and documents. In this paper, we propose a topic-based personalized ranking model (TPRM) that integrates user topical profile with pretrained contextualized term representations to tailor the general document ranking list. Experiments on the real-world dataset demonstrate that TPRM outperforms state-of-the-art ad-hoc ranking models and personalized ranking models significantly.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsInformation Retrieval and Search Behavior · Topic Modeling · Recommender Systems and Techniques
