Deakin University
Browse
paradies-largeexpert-2019.pdf (45.03 MB)

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

Download (45.03 MB)
journal contribution
posted on 2019-01-01, 00:00 authored by Peter Brown, Aik-Choon Tan, Mohamed A El-Esawi, Thomas Liehr, Oliver Blanck, Douglas P Gladue, Gabriel M F Almeida, Tomislav Cernava, Carlos O Sorzano, Andy W K Yeung, Michael S Engel, Arun Richard Chandrasekaran, Thilo Muth, Martin S Staege, Swapna V Daulatabad, Darius Widera, Junpeng Zhang, Adrian Meule, Ken Honjo, Olivier Pourret, Cong-Cong Yin, Zhongheng Zhang, Marco Cascella, Willy A Flegel, Carl S Goodyear, Mark J van Raaij, Zuzanna Bukowy-Bieryllo, Luca G Campana, Nicholas A Kurniawan, David Lalaouna, Felix J Huttner, Brooke A Ammerman, Felix Ehret, Paul A Cobine, Ene-Choo Tan, Hyemin Han, Wenfeng Xia, Christopher McCrum, Ruud P M Dings, Francesco Marinello, Henrik Nilsson, Brett Nixon, Konstantinos Voskarides, Long Yang, Vincent D Costa, Johan Bengtsson-Palme, William Bradshaw, Dominik G Grimm, Nitin Kumar, Elvis Martis, Daniel Prieto, Sandeep C Sabnis, Said E D R Amer, Alan W C Liew, Paul Perco, Farid Rahimi, Giuseppe Riva, Chongxing Zhang, Hari P Devkota, Koichi Ogami, Zarrin Basharat, Walter Fierz, Robert Siebers, Kok-Hian Tan, Karen A Boehme, Peter Brenneisen, James A L Brown, Brian P Dalrymple, David J Harvey, Grace Ng, Sebastiaan Werten, Mark Bleackley, Zhanwu Dai, Raman Dhariwal, Yael Gelfer, Marcus D Hartmann, Pawel Miotla, Radu Tamaian, Pragashnie Govender, Oliver J Gurney-Champion, Joonas H Kauppila, Xiaolei Zhang, Natalia Echeverria, Santhilal Subhash, Hannes Sallmon, Marco Tofani, Taeok Bae, Oliver Bosch, Paraic O Cuiv, Antoine Danchin, Barthelemy Diouf, Tuomas Eerola, Evangelos Evangelou, Fabian V Filipp, Hannes Klump, Lukasz Kurgan, Simon S Smith, Olivier Terrier, Neil Tuttle, David B Ascher
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 research.

History

Journal

Database : the Journal of Biological Databases and Curation

Pagination

1 - 66

Publisher

Oxford University Press

Location

Oxford, Eng.

ISSN

1758-0463

Language

eng

Notes

In Press

Publication classification

C1 Refereed article in a scholarly journal