Filters








79,384 Hits in 5.6 sec

Effective Distributed Representations for Academic Expert Search [article]

Mark Berger, Jakub Zavrel, Paul Groth
2020 arXiv   pre-print
Here, we study how different distributed representations of academic papers (i.e. embeddings) impact academic expert retrieval.  ...  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  ...  Wouter Weerkamp from Zeta Alpha for his valuable feedback and assessment of the work.  ... 
arXiv:2010.08269v1 fatcat:w674vfti75awvals6sp5pkpmcy

Review of: "Effective distributed representations for academic expert search"

Silvio Peroni
2020 Qeios  
This work describes how different approaches based on embeddings to represent scholarly documents (e.g. journal articles and conference papers) can be used to implement systems for experts search in scholarly  ...  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 with different  ...  Other general comments authors run that work and how embedding-based algorithms for expert finding can be used in critical applicative contexts.  ... 
doi:10.32388/oesq6y fatcat:fbh62t6mjfcotoi74myqom62im

Effective distributed representations for academic expert search

Mark Berger, Jakub Zavrel, Paul Groth
2020 Proceedings of the First Workshop on Scholarly Document Processing   unpublished
Here, we study how different distributed representations of academic papers (i.e. embeddings) impact academic expert retrieval.  ...  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  ...  Acknowledgements We would like to thank the reviewers for their insightful commentary. Additionally, we would like to thank dr.  ... 
doi:10.18653/v1/2020.sdp-1.7 fatcat:fy74dkgctjbpjgg4vhbagqtbla

Experts vs. Novices Tagging Behavior: An Exploratory Analysis

Sonja Špiranec, Tomislav Ivanjko
2013 Procedia - Social and Behavioral Sciences  
The authors present results of a study in tagging behavior of an expert and novice group of users.  ...  Differences of the two user groups in tag assignment are being analyzed with regard to tag number and distribution, both by using descriptive statistic and by introducing the tag efficiency measure.  ...  Figure 1 illustrates the tag frequency distribution, where top 10 tags for the expert group were responsible for almost 50% of entire expert tags (160), a distribution that follows the power law.  ... 
doi:10.1016/j.sbspro.2013.02.076 fatcat:lejkyzoycrge3jkl224z4li5ku

Transforming our conversation of information architecture with structure

Nathaniel Davis
2013 Bulletin of the American Society for Information Science and Technology  
The first search involves identifying the most adequate representational framework for the problem; the second search involves locating the best design solution within the framework and translating it  ...  Though invisible and often taken for granted, effective structure is the quality that makes websites functional.  ...  The first search involves identifying the most adequate representational framework for the problem; the second search involves locating the best design solution within the framework and translating it  ... 
doi:10.1002/bult.2013.1720390510 fatcat:mi5tuksr3bcrnkyexapy4vefqu

A Weakly Supervised Academic Search Model Based on Knowledge-Enhanced Feature Representation

Mingying Xu, Junping Du, Feifei Kou, Meiyu Liang, Xin Xu, Jiaxin Yang, Bo Rong
2021 Wireless Communications and Mobile Computing  
For Academic Search, this paper proposes a novel weakly supervised academic search model based on knowledge-enhanced feature representation.  ...  Combining Internet of Things technology and academic search to build academic search framework based on Internet of Things is an effective solution to realize massive academic resource search.  ...  Experimental results show that our method is effective for academic search.  ... 
doi:10.1155/2021/4411524 fatcat:lyr4chjq45bsllawmwnrpqyiz4

A New Model for Probabilistic Information Retrieval on the Web [chapter]

Gabriel Mateescu
2004 Statistics: A Series of Textbooks and Monographs  
Recently, however, academic research has taken root in search engines.  ...  the model's main probability distribution.  ...  More recently, however, academic research has taken root in search engines such as Google [BMPW98] .  ... 
doi:10.1201/9781420030884.ch19 fatcat:7l53ojw4dnde7drrhq7zbq7nxi

Remedies against the Vocabulary Gap in Information Retrieval [article]

Christophe Van Gysel
2017 arXiv   pre-print
Search engines rely heavily on term-based approaches that represent queries and documents as bags of words.  ...  It is the alleviation of the effect brought forward by this vocabulary gap that is the topic of this dissertation.  ...  In particular, we show how representations of experts in the academic domain encode the co-author graph.  ... 
arXiv:1711.06004v1 fatcat:6vkhvfby3zbzrepgopunm7gie4

Ranking experts using author-document-topic graphs

Sujatha Das Gollapalli, Prasenjit Mitra, C. Lee Giles
2013 Proceedings of the 13th ACM/IEEE-CS joint conference on Digital libraries - JCDL '13  
Expert search or recommendation involves the retrieval of people (experts) in response to a query and on occasion, a given set of constraints.  ...  In this paper, we address expert recommendation in academic domains that are different from web and intranet environments studied in TREC.  ...  In academic domains, an expert search system that allows queries based on topics and expert names has several potential applications.  ... 
doi:10.1145/2467696.2467707 dblp:conf/jcdl/GollapalliMG13 fatcat:bwusf5ghn5h2ppr6zz27j7phu4

PostAc : A Visual Interactive Search, Exploration, and Analysis Platform for PhD Intensive Job Postings

Chenchen Xu, Inger Mewburn, Will J Grant, Hanna Suominen
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations  
As a result, typing in PhD to a job search engine tends to return mostly academic jobs. We set out to make the market for advanced research skills more visible to job seekers.  ...  The platform is underpinned by research on the key factors that identify what an employer is looking for when they want to hire a highly skilled researcher.  ...  We gratefully acknowledge the funding from the Data61/CSIRO for the first author's PhD studies.  ... 
doi:10.18653/v1/p19-3008 dblp:conf/acl/XuMGS19 fatcat:zbqe3prum5faxjbym6uxrvxk5y

Group topic modeling for academic knowledge discovery

Ali Daud, Faqir Muhammad
2011 Applied intelligence (Boston)  
Conference mining and expert finding are useful academic knowledge discovery problems from an academic recommendation point of view.  ...  Detailed empirical evaluation shows that our proposed GL methods significantly outperformed DL methods for conference mining and expert finding problems.  ...  Several methods proposed for academic knowledge discovery or related problems can be categorized into three major frameworks (1) graph connectivity based approaches as a basis for representation and analysis  ... 
doi:10.1007/s10489-011-0302-3 fatcat:hfd6kevyo5eb5kpwmkvnh4bx5a

Evaluation-Dependent Representation in Risk Defusing

Oswald Huber
2017 Frontiers in Psychology  
Search for an RDO often involves a price (money, time, effort, etc.) , and at the start it is unclear whether the search turns out to be effective.  ...  This paper treats the effect of the evaluation of outcomes on the representation in a decision process.  ...  accepted academic practice.  ... 
doi:10.3389/fpsyg.2017.00836 pmid:28588540 pmcid:PMC5440553 fatcat:q2kmzcwzxzhwveubkbbq3p25qm

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

Paolo Cifariello, Paolo Ferragina, Marco Ponza
2018 arXiv   pre-print
We present WISER, a new semantic search engine for expert finding in academia.  ...  The effectiveness of our system is established over a large-scale experimental test on a standard dataset for this task.  ...  latent representation of academic experts from the dataset at hand.  ... 
arXiv:1805.03947v1 fatcat:jsm2uonx2bcupiy56sfkgbhtqm

On Information-Theoretic Document-Person Associations for Expert Search in Academia

Vitor Mangaravite, Rodrygo L.T. Santos
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
State-of-the-art expert search approaches rely on documentperson associations to infer the expertise of a candidate person for a given query.  ...  Through a largescale user study with academic experts from several areas of knowledge, we demonstrate the suitability of the proposed association and normalization schemes to improve the effectiveness  ...  Other textual representations showed similar effectiveness.  ... 
doi:10.1145/2911451.2914751 dblp:conf/sigir/MangaraviteS16 fatcat:syq37trzsze7norrtoj6sxud4q

Search Engines and Expertise about Global Issues: Well-defined Landscape or Undomesticated Wilderness? [chapter]

J. Fry, S. Virkar, R. Schroeder
2008 Web Search  
.), Web Searching: Interdisciplinary Perspectives. 255 Summary This chapter investigates the 'winner-takes-all' hypothesis in relation to how academic researchers access online sources and resources.  ...  We found there to be no uniform 'winner-takes-all' effect in the use of online resources.  ...  The representation of the academic domain (e.g. .edu and .ac.uk) is low within each of the case studies except for Internet and Society, whereas the .org domain accounts for the largest percentage of domains  ... 
doi:10.1007/978-3-540-75829-7_14 fatcat:26oyretre5dj5hhxzwicqorzuq
« Previous Showing results 1 — 15 out of 79,384 results