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

A hybrid method for relation extraction from biomedical literature.

Minlie Huang1, Xiaoyan Zhu, Ming Li

  • 1State Key Laboratory of Intelligent Technology and Systems (LITS), Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China.

International Journal of Medical Informatics
|August 13, 2005
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

Application of beta-(2-chloroaroyl) thioacetanilides in synthesis: an unusual and highly efficient access to thiochromeno[2,3-b]pyridine derivatives.

The Journal of organic chemistry·2008
Same author

Gab1 but not Grb2 mediates tumor progression in Met overexpressing colorectal cancer cells.

Carcinogenesis·2008
Same author

Long-term donor-specific tolerance in rat cardiac allografts by intrabone marrow injection of donor bone marrow cells.

Transplantation·2008
Same author

Lsr2 of Mycobacterium tuberculosis is a DNA-bridging protein.

Nucleic acids research·2008
Same author

Amphetamine selectively enhances avoidance responding to a less salient stimulus in rats.

Journal of neural transmission (Vienna, Austria : 1996)·2008
Same author

Retrospective analysis of anterior correction and fusion for adolescent idiopathic thoracolumbar/lumbar scoliosis: the relationship between preserving mobile segments and trunk balance.

International orthopaedics·2008

This study introduces a hybrid shallow parsing and pattern matching method for extracting protein-protein interactions from biomedical texts, achieving improved precision and F-score compared to traditional methods.

Area of Science:

  • Biomedical Informatics
  • Computational Biology
  • Natural Language Processing

Background:

  • Extracting biological relations from literature is crucial but challenging.
  • Existing methods struggle with complex biomedical text grammar.
  • Appositive and coordinative structures in biomedical texts remain largely unaddressed.

Purpose of the Study:

  • To develop a novel hybrid approach for extracting protein-protein interactions.
  • To address limitations of current parsing-based and pattern-based relation extraction methods.
  • To effectively handle complex grammatical structures in biomedical literature.

Main Methods:

  • A hybrid approach combining shallow parsing and pattern matching was developed.
  • Appositive and coordinative structures were interpreted using shallow parsing with syntactic and semantic constraints.

Related Experiment Videos

  • Long sentences were split into sub-sentences for relation extraction via a greedy pattern matching algorithm with auto-generated patterns.

    • Main Results:

    • The approach achieved an 80% F-score on individual verbs and 66% on all verbs for protein-protein interaction extraction.
    • Shallow parsing analysis significantly improved pattern matching performance.
    • The method demonstrated a 7% improvement in precision and F-score over traditional pattern matching and achieved comparable performance to state-of-the-art systems.

    Conclusions:

    • The proposed hybrid method effectively extracts protein-protein interactions from biomedical texts.
    • The approach successfully handles complex grammatical structures common in biomedical literature.
    • This work offers a robust solution for biological relation extraction, advancing the field of biomedical text mining.