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 Video

Updated: Mar 22, 2026

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

1.3K

Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding.

Rie Johnson1, Tong Zhang2

  • 1RJ Research Consulting, Tarrytown, NY, USA.

Advances in Neural Information Processing Systems
|April 19, 2016
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Region of Convergence01:17

Region of Convergence

1.0K
The z-transform is a powerful mathematical tool used in the analysis of discrete-time signals and systems. It is a crucial tool in the analysis of discrete-time systems, but its convergence is limited to specific values of the complex variable z. This range of values, known as the Region of Convergence (ROC), is fundamental in determining the behavior and stability of a system or signal. The ROC defines the region in the complex plane where the z-transform converges, which can take various...
1.0K

You might also read

Related Articles

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

Sort by
Same author

A Framework of Composite Functional Gradient Methods for Generative Adversarial Models.

IEEE transactions on pattern analysis and machine intelligence·2019
Same author

Learning Nonlinear Functions Using Regularized Greedy Forest.

IEEE transactions on pattern analysis and machine intelligence·2015
Same author

Sequence-based antigenic change prediction by a sparse learning method incorporating co-evolutionary information.

PloS one·2014
Same author

Longitudinal changes in total, 2-LTR circular, and integrated HIV-1 DNA during the first year of HIV-1 infection in CD4Low and CD4High patient groups with HIV-1 subtype AE.

Viral immunology·2014
Same author

Bacterial assembly and temporal dynamics in activated sludge of a full-scale municipal wastewater treatment plant.

The ISME journal·2014
Same author

Experimental evidence for s-wave pairing symmetry in superconducting Cu(x)Bi2Se3 single crystals using a scanning tunneling microscope.

Physical review letters·2014

This study introduces a novel semi-supervised framework using convolutional neural networks (CNNs) for text categorization. The method learns text region embeddings from unlabeled data, outperforming prior methods in sentiment and topic classification.

Area of Science:

  • Artificial Intelligence
  • Natural Language Processing
  • Machine Learning

Background:

  • Traditional text categorization relies heavily on pre-trained word embeddings.
  • Existing methods often require large amounts of labeled data for effective training.
  • Limitations exist in capturing nuanced semantic information from text using conventional approaches.

Purpose of the Study:

  • To propose a novel semi-supervised framework for text categorization.
  • To develop a method for learning text region embeddings from unlabeled data.
  • To improve the performance of convolutional neural networks (CNNs) in text classification tasks.

Main Methods:

  • A semi-supervised learning framework integrating convolutional neural networks (CNNs).
  • Learning embeddings of small text regions using a two-view semi-supervised approach on unlabeled data.

Related Experiment Videos

Last Updated: Mar 22, 2026

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

1.3K
  • Integrating learned embeddings into a supervised CNN for classification.

    • Main Results:

    • The proposed framework achieved superior performance compared to previous approaches.
    • Demonstrated effectiveness on both sentiment classification and topic classification tasks.
    • The learned embeddings from unlabeled data proved beneficial for supervised tasks.

    Conclusions:

    • The novel semi-supervised framework offers an effective alternative for text categorization.
    • Learning text region embeddings from unlabeled data enhances CNN performance.
    • This approach reduces the dependency on large labeled datasets for text classification.