Large expert-curated database for benchmarking document similarity detection in biomedical literature search


Peter Brown, Griffith University
Yaoqi Zhou, Griffith University
Aik Choon Tan, University of Colorado Anschutz Medical Campus
Mohamed A. El-Esawi, University of Tanta
Thomas Liehr, Universitätsklinikum Jena und Medizinische Fakultät
Oliver Blanck, Universitätsklinikum Schleswig-Holstein Campus Kiel
Douglas P. Gladue, USDA Agricultural Research Service, Washington DC
Gabriel M.F. Almeida, University of Jyvaskyla
Tomislav Cernava, Technische Universitat Graz
Carlos O. Sorzano, CSIC - Centro Nacional de Biotecnologia (CNB)
Andy W.K. Yeung, The University of Hong Kong
Michael S. Engel, University of Kansas
Arun R. Chandrasekaran, Confer Health, Inc.
Thilo Muth, Robert Koch Institut
Martin S. Staege, Martin-Universität Halle-Wittenberg
Swapna V. Daulatabad, Indiana University-Purdue University
Darius Widera, University of Reading
Junpeng Zhang, Dali University
Adrian Meule, Universitat Salzburg
Ken Honjo, University of Tsukuba
Olivier Pourret, UniLaSalle
Cong Cong Yin, Henry Ford Health System
Zhongheng Zhang, Zhejiang University
Marco Cascella, Istituto Nazionale Tumori IRCCS - Fondazione G Pascale, Napoli
Willy A. Flegel, National Institutes of Health (NIH)
Carl S. Goodyear, University of Glasgow
Mark J. van Raaij, CSIC - Centro Nacional de Biotecnologia (CNB)
Zuzanna Bukowy-Bieryllo, Polish Academy of Sciences
Luca G. Campana, Università degli Studi di Padova
Nicholas A. Kurniawan, Technische Universiteit Eindhoven
David Lalaouna, Université de Strasbourg
Felix J. Hüttner, Universität Heidelberg
Brooke A. Ammerman, University of Notre Dame

Document Type


Publication Date



© The Author(s) 2019. Published by Oxford University Press. Document recommendation systems for locating relevant literature have mostly relied on methods developed a decade ago. This is largely due to the lack of a large offline gold-standard benchmark of relevant documents that cover a variety of research fields such that newly developed literature search techniques can be compared, improved and translated into practice. To overcome this bottleneck, we have established the RElevant LIterature SearcH consortium consisting of more than 1500 scientists from 84 countries, who have collectively annotated the relevance of over 180 000 PubMed-listed articles with regard to their respective seed (input) article/s. The majority of annotations were contributed by highly experienced, original authors of the seed articles. The collected data cover 76% of all unique PubMed Medical Subject Headings descriptors. No systematic biases were observed across different experience levels, research fields or time spent on annotations. More importantly, annotations of the same document pairs contributed by different scientists were highly concordant. We further show that the three representative baseline methods used to generate recommended articles for evaluation (Okapi Best Matching 25, Term Frequency-Inverse Document Frequency and PubMed Related Articles) had similar overall performances. Additionally, we found that these methods each tend to produce distinct collections of recommended articles, suggesting that a hybrid method may be required to completely capture all relevant articles. The established database server located at https://relishdb.ict.griffith.edu.au is freely available for the downloading of annotation data and the blind testing of new methods. We expect that this benchmark will be useful for stimulating the development of new powerful techniques for title and title/abstract-based search engines for relevant articles in biomedical science.

Publication Name


Volume Number


First Page


Last Page




This document is currently not available here.