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 neural joint model for entity and relation extraction from biomedical text.

Fei Li1, Meishan Zhang2, Guohong Fu2

  • 1School of Computer, Wuhan University, Bayi Road, Wuhan, China.

BMC Bioinformatics
|April 1, 2017
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

Antiosteoporotic activity of echinacoside in ovariectomized rats.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2013
Same author

Low molecular weight fucoidan against renal ischemia-reperfusion injury via inhibition of the MAPK signaling pathway.

PloS one·2013
Same author

Promoting the activity of catalysts for the oxidation of water with bridged dinuclear ruthenium complexes.

Angewandte Chemie (International ed. in English)·2013
Same author

Tunable green oxygen barrier through layer-by-layer self-assembly of chitosan and cellulose nanocrystals.

Carbohydrate polymers·2013
Same author

Gastrointestinal effects of resistant starch, soluble maize fibre and pullulan in healthy adults.

The British journal of nutrition·2013
Same author

GeneExpressionSignature: an R package for discovering functional connections using gene expression signatures.

Omics : a journal of integrative biology·2013

This study introduces a novel neural joint model for extracting biomedical entities and relations, improving accuracy and reducing feature engineering. The model enhances biomedical text mining by jointly processing tasks, outperforming previous methods.

Area of Science:

  • Biomedical Informatics
  • Natural Language Processing
  • Machine Learning

Background:

  • Biomedical entity and relation extraction is crucial for research.
  • Traditional pipeline models require extensive feature engineering and suffer from error propagation.
  • Existing methods struggle to capture interactions between subtasks.

Purpose of the Study:

  • To propose a neural joint model for simultaneous extraction of biomedical entities and their relations.
  • To overcome limitations of feature-based pipeline models in biomedical text mining.
  • To improve efficiency and accuracy in extracting complex biomedical information.

Main Methods:

  • Developed a neural joint model for end-to-end extraction of entities and relations.
  • The model processes multiple subtasks simultaneously, enabling parameter sharing.
Keywords:
Biomedical textEntity recognitionJoint modelNeural networkRelation extraction

Related Experiment Videos

  • Applied deep learning techniques to biomedical text data.

    • Main Results:

    • Achieved significant improvements on two benchmark tasks: adverse drug event extraction and bacteria-host relation extraction.
    • Improved F1 scores by 5.1% (entity recognition) and 8.0% (relation extraction) for drug-disease relations.
    • Enhanced relation extraction F1 score by 9.2% for bacteria-location relations.

    Conclusions:

    • The proposed neural joint model demonstrates competitive performance with reduced feature engineering.
    • Neural network-based approaches are effective for biomedical entity and relation extraction.
    • Parameter sharing offers an efficient method for joint task processing in biomedical NLP.