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

An unsupervised method for the extraction of propositional information from text.

Simon Dennis1

  • 1Institute of Cognitive Science, University of Colorado, Boulder, CO 80301, USA. dennissj@psych.colorado.edu

Proceedings of the National Academy of Sciences of the United States of America
|March 17, 2004
PubMed
Summary

This study introduces a memory-based model for automatically extracting knowledge from text, improving question-answering systems. It enables inference from implicit information, overcoming limitations of manual knowledge base creation.

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

Duration Is Not a Reliable Indicator for Anticipating Event Boundaries.

Computational brain & behavior·2026
Same author

Private speech: similarities between a large language model and children.

Frontiers in artificial intelligence·2026
Same author

Practitioner Perspectives on the Uses of Generative AI Chatbots in Mental Health Care: Mixed Methods Study.

JMIR human factors·2025
Same author

Examining the Dose-Response Effects of Mindfulness Meditation Interventions on Well-Being: Protocol for a Randomized Controlled Trial.

JMIR research protocols·2025
Same author

Balancing risks and benefits: clinicians' perspectives on the use of generative AI chatbots in mental healthcare.

Frontiers in digital health·2025
Same author

Corrigendum to "Does TikTok contribute to eating disorders? A comparison of the TikTok algorithms belonging to individuals with eating disorders versus healthy controls" [Body Image 51 (2024) 101807].

Body image·2024

Area of Science:

  • Natural Language Processing
  • Artificial Intelligence
  • Computational Linguistics

Background:

  • Question-answering systems benefit from propositional analysis and formal inference.
  • Manual knowledge base creation is labor-intensive and limits domain adaptability.

Purpose of the Study:

  • To address limitations of manual knowledge base creation in question-answering systems.
  • To demonstrate autonomous propositional knowledge extraction using a memory-based model.

Main Methods:

  • Utilized the Syntagmatic Paradigmatic model, a memory-based approach to sentence processing.
  • Employed String Edit Theory for aligning new sentences with stored instances from memory.
  • Extracted propositional knowledge autonomously from unannotated text.

Related Experiment Videos

Main Results:

  • The model successfully answered questions with explicitly stated facts.
  • Demonstrated "inference by coincidence" for implicit information extraction.
  • Accurately determined tennis match winners from web-reported data.

Conclusions:

  • Autonomous propositional knowledge extraction is feasible and effective.
  • Memory-based sentence processing offers a robust alternative to manual knowledge engineering.
  • The Syntagmatic Paradigmatic model shows promise for enhancing question-answering capabilities.