Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Leveraging shortest dependency paths in low-resource biomedical relation extraction.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read Online Read More Add to Saved list
  • Author(s): Enayati S;Enayati S; Vucetic S; Vucetic S
  • Source:
    BMC medical informatics and decision making [BMC Med Inform Decis Mak] 2024 Jul 24; Vol. 24 (1), pp. 205. Date of Electronic Publication: 2024 Jul 24.
  • Publication Type:
    Journal Article
  • Language:
    English
  • Additional Information
    • Source:
      Publisher: BioMed Central Country of Publication: England NLM ID: 101088682 Publication Model: Electronic Cited Medium: Internet ISSN: 1472-6947 (Electronic) Linking ISSN: 14726947 NLM ISO Abbreviation: BMC Med Inform Decis Mak Subsets: MEDLINE
    • Publication Information:
      Original Publication: London : BioMed Central, [2001-
    • Subject Terms:
      Natural Language Processing* ; Data Mining*/methods; Humans ; Machine Learning
    • Abstract:
      Background: Biomedical Relation Extraction (RE) is essential for uncovering complex relationships between biomedical entities within text. However, training RE classifiers is challenging in low-resource biomedical applications with few labeled examples.
      Methods: We explore the potential of Shortest Dependency Paths (SDPs) to aid biomedical RE, especially in situations with limited labeled examples. In this study, we suggest various approaches to employ SDPs when creating word and sentence representations under supervised, semi-supervised, and in-context-learning settings.
      Results: Through experiments on three benchmark biomedical text datasets, we find that incorporating SDP-based representations enhances the performance of RE classifiers. The improvement is especially notable when working with small amounts of labeled data.
      Conclusion: SDPs offer valuable insights into the complex sentence structure found in many biomedical text passages. Our study introduces several straightforward techniques that, as demonstrated experimentally, effectively enhance the accuracy of RE classifiers.
      (© 2024. The Author(s).)
    • References:
      Nature. 2002 May 23;417(6887):399-403. (PMID: 12000970)
      N Engl J Med. 2005 May 26;352(21):2211-21. (PMID: 15917386)
      Int J Clin Pharmacol Ther. 2000 Nov;38(11):504-13. (PMID: 11097142)
      PLoS One. 2013 Apr 17;8(4):e60954. (PMID: 23613763)
      BMC Med Inform Decis Mak. 2019 Jan 31;19(Suppl 1):22. (PMID: 30700301)
      Artif Intell Med. 2005 Feb;33(2):139-55. (PMID: 15811782)
      BMC Bioinformatics. 2008 Nov 19;9 Suppl 11:S2. (PMID: 19025688)
      AMIA Annu Symp Proc. 2020 Mar 04;2019:1236-1245. (PMID: 32308921)
      PLoS Comput Biol. 2010 Jul 01;6:e1000837. (PMID: 20617200)
      Bioinformatics. 2018 Mar 1;34(5):828-835. (PMID: 29077847)
      Nucleic Acids Res. 2006 Jan 1;34(Database issue):D668-72. (PMID: 16381955)
      Nucleic Acids Res. 1997 Jan 1;25(1):31-6. (PMID: 9016499)
      Bioinformatics. 2020 Feb 15;36(4):1234-1240. (PMID: 31501885)
    • Contributed Indexing:
      Keywords: BERT; Low-resource; Natural language processing; Relation extraction; Shortest dependency path
    • Publication Date:
      Date Created: 20240725 Date Completed: 20240725 Latest Revision: 20240728
    • Publication Date:
      20240728
    • Accession Number:
      PMC11267752
    • Accession Number:
      10.1186/s12911-024-02592-2
    • Accession Number:
      39049015