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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Knowledge-guided contextual gene set analysis with large language models.

Bioinformatics (Oxford, England)·2026
Same author

PXN Unlocks the Power of Public Gene Expression Data Through Cross-Technology Integration.

bioRxiv : the preprint server for biology·2026
Same author

GeneAgent: self-verification language agent for gene-set analysis using domain databases.

Nature methods·2025
Same author

Enhancing biomedical relation extraction with directionality.

Bioinformatics (Oxford, England)·2025
Same author

LitSense 2.0: AI-powered biomedical information retrieval with sentence and passage level knowledge discovery.

Nucleic acids research·2025
Same author

PubMed Computed Authors in 2024: an open resource of disambiguated author names in biomedical literature.

Bioinformatics (Oxford, England)·2024

Related Experiment Video

Updated: Sep 1, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

675

Pre-trained models, data augmentation, and ensemble learning for biomedical information extraction and document

Arslan Erdengasileng1, Qing Han1, Tingting Zhao2

  • 1Department of Statistics, Florida State University, Tallahassee, FL 32306, USA.

Database : the Journal of Biological Databases and Curation
|August 13, 2022
PubMed
Summary
This summary is machine-generated.

Researchers optimized natural language processing (NLP) for biomedical text by using pre-trained NLP models, data augmentation, and ensemble modeling. These strategies enhance information extraction and document classification in the rapidly growing field of biomedical science.

More Related Videos

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

864
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

551

Related Experiment Videos

Last Updated: Sep 1, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

675
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

864
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

551

Area of Science:

  • Biomedical Informatics
  • Computational Biology
  • Natural Language Processing

Background:

  • The rapid increase in biomedical publications necessitates advanced methods for processing unstructured text data.
  • Effective natural language processing (NLP) is crucial for tasks like document classification and information extraction in the biomedical domain.
  • The BioCreative Challenge evaluates and promotes the development of information extraction methods within the biomedical community.

Purpose of the Study:

  • To summarize the authors' work and findings from participating in the BioCreative Challenge VII.
  • To identify key components for achieving high performance in various NLP tasks within the biomedical domain.
  • To evaluate the effectiveness of pre-trained models, data augmentation, and ensemble modeling for biomedical NLP.

Main Methods:

  • Participation in all five tracks of the BioCreative Challenge VII.
  • Application of pre-trained NLP models.
  • Implementation of data augmentation strategies.
  • Utilization of ensemble modeling techniques.

Main Results:

  • Three core components were identified for high performance across diverse NLP tasks: pre-trained NLP models, data augmentation, and ensemble modeling.
  • Tailoring these strategies to specific tasks yields high-performing baseline models suitable for practical applications.
  • Task-specific methods can provide additional, albeit often small, performance improvements, crucial for competitive outcomes.

Conclusions:

  • A combination of pre-trained NLP models, data augmentation, and ensemble modeling provides a robust framework for biomedical NLP tasks.
  • The identified strategies offer effective solutions for managing and extracting information from large biomedical text corpora.
  • The findings contribute to advancing NLP capabilities in the biomedical sciences, supporting efficient knowledge discovery.