WISER: A Semantic Approach for Expert Finding in Academia based on Entity Linking

TL;DR

WISER is a semantic expert-finding system for academia that combines language models with Wikipedia's knowledge graph to improve retrieval accuracy by modeling author expertise through entity linking and graph-based profiles.

Contribution

The paper introduces WISER, a novel unsupervised semantic search engine that integrates Wikipedia entity linking with language models for expert finding in academia.

Findings

WISER outperforms existing expert-finding systems on standard datasets.

The system effectively models expertise using Wikipedia-based entity graphs.

WISER demonstrates potential for large-scale academic profiling and technology transfer applications.

Abstract

We present WISER, a new semantic search engine for expert finding in academia. Our system is unsupervised and it jointly combines classical language modeling techniques, based on text evidences, with the Wikipedia Knowledge Graph, via entity linking. WISER indexes each academic author through a novel profiling technique which models her expertise with a small, labeled and weighted graph drawn from Wikipedia. Nodes in this graph are the Wikipedia entities mentioned in the author's publications, whereas the weighted edges express the semantic relatedness among these entities computed via textual and graph-based relatedness functions. Every node is also labeled with a relevance score which models the pertinence of the corresponding entity to author's expertise, and is computed by means of a proper random-walk calculation over that graph; and with a latent vector representation which is learned via entity and other kinds of structural embeddings derived from Wikipedia. At query time, experts are retrieved by combining classic document-centric approaches, which exploit the occurrences of query terms in the author's documents, with a novel set of profile-centric scoring strategies, which compute the semantic relatedness between the author's expertise and the query topic via the above graph-based profiles. The effectiveness of our system is established over a large-scale experimental test on a standard dataset for this task. We show that WISER achieves better performance than all the other competitors, thus proving the effectiveness of modelling author's profile via our "semantic" graph of entities. Finally, we comment on the use of WISER for indexing and profiling the whole research community within the University of Pisa, and its application to technology transfer in our University.