Effective Distributed Representations For Academic Expert Search

Abstract

Expert search aims to find and rank experts based on a user's query. In academia, retrieving experts is an efficient way to navigate through a large amount of academic knowledge. Here, we study how different distributed representations of academic papers (i.e. embeddings) impact academic expert retrieval. We use the Microsoft Academic Graph dataset and experiment with different configurations of a document-centric voting model for retrieval. In particular, we explore the impact of the use of contextualized embeddings on search performance. We also present results for paper embeddings that incorporate citation information through retrofitting. Additionally, experiments are conducted using different techniques for assigning author weights based on author order. We observe that using contextual embeddings produced by a transformer model trained for sentence similarity tasks produces the most effective paper representations for document-centric expert retrieval. However, retrofitting the p

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keyberger2020effective

Related papers

• PARK: Personalized Academic Retrieval With Knowledge-graphs (2025)3.58
• Contrastive Learning And Mixture Of Experts Enables Precise Vector Embeddings (2024)0.00
• Explore Entity Embedding Effectiveness In Entity Retrieval (2019)4.52
• Improving Embedding With Contrastive Fine-tuning On Small Datasets With Expert-augmented Scores (2024)0.00
• Unified Embedding Based Personalized Retrieval In Etsy Search (2023)2.26
• Routerretriever: Routing Over A Mixture Of Expert Embedding Models (2024)0.00
• Neural IR Meets Graph Embedding: A Ranking Model For Product Search (2019)11.85
• Investigating Mixture Of Experts In Dense Retrieval (2024)0.00