Wiser: A semantic approach for expert finding in academia based on entity linking

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 largescale 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.

Swat: A system for detecting salient Wikipedia entities in texts

“…Finally, we mention the problem of testing our approach and the other known ones over datasets of a different type than news and over other promising domains, such as expert finding in academia . Despite a different kind of textual data, our system Swat could actually be able to correctly detect the salient entities both in web pages and research papers in a similar fashion as already done with news: classical information extraction systems designed their algorithms only on the top of positional and frequency signals (which are also deployed by Swat ), but without using Wikipedia entities (and relative annotation‐ and relatedness‐based features) as salient elements.…”

Expert Finding Systems: A Systematic Review

“…Most of the generative probabilistic models and voting models cannot mine the hidden information that can be found in social networks and that cannot be mined from the documents, and they are 'one-step' relevance models [4]. The authors of reference [46] deployed entity linking, relatedness, and entity embeddings to create a novel WEM profile for academia experts. They built their model based on a weighted and labeled graph drawn from Wikipedia.…”

“…It contains both Dutch and English documents, and it has five different ground-truths-GT1 to GT5. GT5 is considered the most recent and complete ground-truth [46]. Additionally, CiteSeer and DBLP offer the information of computer scientific literatures on main journals and conference proceedings.…”

DWIE: An entity-centric dataset for multi-task document-level information extraction

“…For example, an application such as question answering may be improved by relying on relation extraction (RE) (Hu et al, 2019;Yu et al, 2017), coreference resolution (Bhattacharjee et al, 2020;Gao et al, 2019), named entity recognition (NER) (Molla et al, 2006;Singh et al, 2018), and entity linking (EL) (Broscheit, 2019;Chen et al, 2017) components. This also holds for other applications such as personalized news recommendation (Karimi et al, 2018;Wang et al, 2018Wang et al, , 2019, fact checking (Thorne & Vlachos, 2018;Zhang & Ghorbani, 2020), opinion mining (Sun et al, 2017), semantic search (Cifariello et al, 2019), and conversational agents (Roller et al, 2020). The last decade has shown a growing interest in IE datasets suitably annotated for developing multi-task models where each of the tasks (e.g., NER, RE, etc.)…”