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 network model with feature selection for Korean speech act classification.

Kyungsun Kim1, Harksoo Kim, Jungyun Seo

  • 1Department of Computer Science, Sogang University, 1 Sinsu-dong, Mapo-gu, Seoul, 121-742, Korea. kksun@nlprep.sogang.ac.kr

International Journal of Neural Systems
|February 17, 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

Polluted air and fading memory: Effects of air pollution on Alzheimer's disease and vascular dementia.

Journal of the Air & Waste Management Association (1995)·2026
Same author

Shadows in the Air: Mental health vulnerabilities under PM10 and PM2.5, before and after COVID-19.

SSM - population health·2025
Same author

Effectiveness of intravenous thrombolysis in patients with large-vessel occlusion receiving endovascular treatment in Korea.

Acute and critical care·2025
Same author

Concurrence of Subacute Combined Degeneration and Deep Vein Thrombosis After Chronic Nitrous Oxide Abuse.

Journal of clinical neurology (Seoul, Korea)·2025
Same author

LOGIC: LLM-originated guidance for internal cognitive improvement of small language models in stance detection.

PeerJ. Computer science·2024
Same author

Effective sentence-level relation extraction model using entity-centric dependency tree.

PeerJ. Computer science·2024

This study introduces a Korean speech act classification model using neural networks and morphological feature selection. The approach improves precision and reduces training time for better dialogue understanding systems.

Area of Science:

  • Natural Language Processing
  • Computational Linguistics
  • Artificial Intelligence

Background:

  • Speech act classification is crucial for understanding user intent in dialogue systems.
  • Existing models often rely on complex linguistic features.

Purpose of the Study:

  • To propose a neural network model for Korean speech act classification.
  • To develop a method for extracting and selecting effective morphological features.

Main Methods:

  • A neural network model was developed for Korean speech act classification.
  • A feature selection method was applied to extract and choose optimal morphological features from utterances.

Main Results:

  • The proposed neural network model demonstrated improved precision and reduced training time.

Related Experiment Videos

  • The model outperformed existing methods that use high-level linguistic features.

    • Conclusions:

    • The proposed neural network model is effective for Korean speech act classification and adaptable to other domains.
    • Effective feature selection is key to converting surface sentences into fixed-dimension vectors for neural networks in speech act classification.