Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Constructing biological knowledge bases by extracting information from text sources.

M Craven1, J Kumlien

  • 1School of Computer Science, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213-3891, USA. mark.craven@cs.cmu.edu

Proceedings. International Conference on Intelligent Systems for Molecular Biology
|April 29, 2000
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Exploration of key stakeholder views and experience of specialist schools' food: a qualitative study.

BMC public health·2026
Same author

Nitric oxide-releasing polyacrylonitrile disperses biofilms formed by wound-relevant pathogenic bacteria.

Journal of applied microbiology·2016
Same author

Fluorescence in-situ hybridization for the identification of bacterial species in archival heart valve sections of canine bacterial endocarditis.

Journal of comparative pathology·2011
Same author

Teaching core content in family medicine.

Canadian family physician Medecin de famille canadien·2011
Same author

Antimicrobial resistance impacts clinical outcome of granulomatous colitis in boxer dogs.

Journal of veterinary internal medicine·2010
Same author

Remission of histiocytic ulcerative colitis in Boxer dogs correlates with eradication of invasive intramucosal Escherichia coli.

Journal of veterinary internal medicine·2009

This study introduces machine learning to extract biological facts from text, like MEDLINE records. This approach enhances data accessibility and knowledge base construction from underutilized text sources.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Natural Language Processing

Background:

  • Molecular biology databases are increasingly accessible, but textual information remains underutilized.
  • Extracting structured biological information from unstructured text sources is a significant challenge.

Purpose of the Study:

  • To develop and evaluate machine learning methods for automatically extracting biological facts from text.
  • To create structured representations of biological information from sources like MEDLINE records.
  • To reduce the cost of training information extraction models using weakly labeled data.

Main Methods:

  • Applied a statistical text classification method for information extraction.
  • Utilized a relational learning method for fact extraction from text.

Related Experiment Videos

  • Investigated learning from weakly labeled training data to decrease costs.

    • Main Results:

    • Demonstrated the feasibility of using machine learning for automated biological fact extraction.
    • Showed initial success in inducing information-extraction routines from text.
    • Presented a viable approach for cost-effective training of extraction models.

    Conclusions:

    • Machine learning offers a powerful approach to unlock biological insights from text.
    • Automated information extraction from text can significantly enhance biological knowledge bases.
    • Weakly supervised learning methods show promise for reducing the burden of data annotation.