Advanced

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

Zhou, Yaoqi and Brown, Peter (2019) In Database : the journal of biological databases and curation 2019.
Abstract
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... (More)
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. (Less)
Please use this url to cite or link to this publication:
author
contributor
LU
author collaboration
organization
publishing date
type
Contribution to journal
publication status
epub
subject
keywords
Medical law, Medicinsk rätt
in
Database : the journal of biological databases and curation
volume
2019
article number
baz085
publisher
Oxford University Press
ISSN
1758-0463
language
English
LU publication?
yes
additional info
Intervention as part of the RELISH Consortium
id
1e4ab8b7-eb72-4fa7-b812-05fd8a53f3ac
date added to LUP
2019-11-27 12:47:06
date last changed
2019-12-02 08:26:55
@article{1e4ab8b7-eb72-4fa7-b812-05fd8a53f3ac,
  abstract     = {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.},
  author       = {Zhou, Yaoqi  and Brown, Peter },
  issn         = {1758-0463},
  language     = {eng},
  month        = {10},
  publisher    = {Oxford University Press},
  series       = {Database : the journal of biological databases and curation},
  title        = {Large expert-curated database for benchmarking document similarity detection in biomedical literature search},
  url          = {https://lup.lub.lu.se/search/ws/files/72654615/Large_expert_curated_database_for_benchmarking_document_similarity_detection_in_biomedical_literature_search.pdf},
  volume       = {2019},
  year         = {2019},
}