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

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 sear...

ver descrição completa

Detalhes bibliográficos
Autor principal: Chowdhury, Mohiuddin Ahsanul Kabir
Formato: Artigo
Idioma:inglês
Publicado em: Oxford University Press 2025
Acesso em linha:https://repository.auw.edu.bd/handle/123456789/883
_version_ 1857449007516745728
author Chowdhury, Mohiuddin Ahsanul Kabir
author_facet Chowdhury, Mohiuddin Ahsanul Kabir
author_sort Chowdhury, Mohiuddin Ahsanul Kabir
collection institutional Repository
description 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.
format Article
id 123456789-883
institution Asian University for Women
language English
publishDate 2025
publisher Oxford University Press
record_format dspace
spelling 123456789-8832026-02-18T06:15:31Z Large expert-curated database for benchmarking document similarity detection in biomedical literature search Chowdhury, Mohiuddin Ahsanul Kabir 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. 2025-07-31T06:52:06Z 2025-07-31T06:52:06Z 2019 Article https://repository.auw.edu.bd/handle/123456789/883 en application/pdf Oxford University Press
spellingShingle Chowdhury, Mohiuddin Ahsanul Kabir
Large expert-curated database for benchmarking document similarity detection in biomedical literature search
title Large expert-curated database for benchmarking document similarity detection in biomedical literature search
title_full Large expert-curated database for benchmarking document similarity detection in biomedical literature search
title_fullStr Large expert-curated database for benchmarking document similarity detection in biomedical literature search
title_full_unstemmed Large expert-curated database for benchmarking document similarity detection in biomedical literature search
title_short Large expert-curated database for benchmarking document similarity detection in biomedical literature search
title_sort large expert curated database for benchmarking document similarity detection in biomedical literature search
url https://repository.auw.edu.bd/handle/123456789/883
work_keys_str_mv AT chowdhurymohiuddinahsanulkabir largeexpertcurateddatabaseforbenchmarkingdocumentsimilaritydetectioninbiomedicalliteraturesearch