Jove
Visualize
Contact Us

Related Experiment Videos

Information extraction from biomedical text.

Jerry R Hobbs1

  • 1USC Information Sciences Institute, Marina del Rey, CA 90292, USA. hobbs@isi.edu

Journal of Biomedical Informatics
|May 21, 2003
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 journal

Causal intervention validation of gene regulatory signals in scGPT.

Journal of biomedical informatics·2026
Same journal

CoAff-DTI: Fine-grained drug-target interaction prediction using pre-trained language models and affinity-guided mechanisms.

Journal of biomedical informatics·2026
Same journal

Evaluation of temporal preservation in synthetic longitudinal patient data.

Journal of biomedical informatics·2026
Same journal

ARKE: An ontology-driven framework for automated mapping of local radiology procedure terms to the LOINC-RadLex playbook using large language model.

Journal of biomedical informatics·2026
Same journal

A validation-driven training controller for cross-lingual biomedical NER via reinforcement learning-based adaptive loss weighting.

Journal of biomedical informatics·2026
Same journal

ASP-HR: An Adaptive Spatial Perception and Hierarchical Reasoning mechanism for document-level biomedical relation extraction.

Journal of biomedical informatics·2026
See all related articles
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

Information extraction (IE) processes text to find specific data like entities and events, offering a practical approach between keyword searches and full text understanding. This technology, applied to biomedical text, could significantly aid data curation efforts.

Area of Science:

  • Natural Language Processing
  • Computational Linguistics
  • Bioinformatics

Background:

  • Information extraction (IE) automates the retrieval of structured data from unstructured text, bridging the gap between simple keyword searches and complex full-text comprehension.
  • IE technology typically employs a staged processing approach, often utilizing cascaded finite-state transducers for linguistic analysis.
  • Early stages focus on domain-independent recognition of linguistic objects, while later stages identify domain-specific patterns.

Purpose of the Study:

  • To explore the application and potential impact of information extraction techniques in the biomedical domain.
  • To evaluate the feasibility of IE for extracting entities, relations, and events from biomedical literature.
  • To assess the utility of IE for supporting curatorial activities in the biomedical field.

Related Experiment Videos

Main Methods:

  • Utilizing cascaded finite-state transducers for a multi-stage text processing pipeline.
  • Developing domain-independent early stages for linguistic object recognition.
  • Implementing domain-dependent later stages to identify specific patterns in biomedical text.

Main Results:

  • Information extraction technology has historically achieved approximately 60% recall and precision in various domains.
  • Initial efforts are underway to adapt IE techniques for processing biomedical text.
  • The potential for IE to significantly assist biomedical curatorial tasks is recognized, even at current performance levels.

Conclusions:

  • Information extraction offers a feasible method for capturing structured information from text, representing a valuable intermediate step towards full text understanding.
  • The staged, domain-independent and domain-dependent processing model is a key characteristic of IE technology.
  • Applying information extraction to biomedical text holds significant promise for enhancing data management and curatorial workflows, despite potential performance limitations.