Effective distributed representations for academic expert search

  title={Effective distributed representations for academic expert search},
  author={Mark J. Berger and Jakub Zavrel and Paul Groth},
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… Expand

Tables from this paper

An Explanatory Query-Based Framework for Exploring Academic Expertise
This paper proposes a novel query-based framework for searching, scoring, and exploring research expertise automatically, based upon processing abstracts of academic publications, and shows that the simple method is effective in identifying matches, while satisfying desirable properties and being efficient. Expand
Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity
This work presents ASPIRE, a new scientific document similarity model based on matching finegrained aspects that improves performance on document similarity tasks across four datasets, and presents a fast method that involves matching only single sentence pairs, and a method that makes sparse multiple matches with optimal transport. Expand
CSFCube - A Test Collection of Computer Science Research Articles for Faceted Query by Example
This work introduces the task of faceted Query by Example in which users can also specify a finer grained aspect in addition to the input query document, and describes an expert annotated test collection to evaluate models trained to perform this task. Expand
A New Neural Search and Insights Platform for Navigating and Organizing AI Research
An overview of the overall architecture of the system and of the components for document analysis, question answering, search, analytics, expert search, and recommendations are given. Expand


Combining Text Embedding and Knowledge Graph Embedding Techniques for Academic Search Engines
Results show that paragraph vectors are effective at capturing the similarity and relatedness among papers and knowledge graph embedding models can preserve the inherent structure of the original knowledge graph and hence assist in link prediction tasks such as co-author inference. Expand
Enhanced Models for Expertise Retrieval Using Community-Aware Strategies
This work proposes a new smoothing method using the community context for statistical language modeling, which is employed to identify the most relevant documents so as to boost the performance of expertise retrieval in the document-based model and develops an adaptive ranking refinement method to enhance expertise retrieval. Expand
Impact of the Query Set on the Evaluation of Expert Finding Systems
This paper describes two datasets extracted from AMiner, three baseline algorithms from the literature based on several document representations and provides experiment results to show that using a wide range of more realistic queries provides different evaluation results to the usual topic-queries. Expand
Integrating multiple windows and document features for expert finding
This work argues that expert finding is more sensitive to multiple levels of associations and document features that current expert finding systems insufficiently address, and proposes a novel approach that integrates the above-mentioned three aspects as well as a query expansion technique in a two-stage model for expert finding. Expand
Learning Embeddings for Academic Papers
This dissertation first studies the norm convergence issue in SGNS and proposes to use an L2 regularization to fix the problem, and experiments show that the method improvesSGNS and its variants on different types of data. Expand
Review of: "Effective distributed representations for academic expert search"
Possible applications Even if this work is entirely on the embeddings-based algorithms for expert finding, the expert finding activity per se has several applications in the scholarly domain all withExpand
Formal models for expert finding in enterprise corpora
This work presents two general strategies to expert searching given a document collection which are formalized using generative probabilistic models, and shows that the second strategy consistently outperforms the first. Expand
P2V: large-scale academic paper embedding
A new neural network based algorithm, called P2V (paper2vector), is proposed to learn high-quality embeddings for academic papers on large-scale datasets and achieves state-of-the-art performance in paper classification, paper similarity, and paper influence prediction task. Expand
Voting techniques for expert search
This paper proposes a novel approach for predicting and ranking candidate expertise with respect to a query, called the Voting Model for Expert Search, and demonstrates that applying field-based weighting models improves the ranking of candidates. Expand
Broad expertise retrieval in sparse data environments
Two main expertise retrieval tasks are presented, along with a set of baseline approaches based on generative language modeling, aimed at finding expertise relations between topics and people, and current techniques appear to be generalizable to other settings. Expand