Simulated Document Parsing Artificial Intelligence System

Abstract

This paper introduces an encoder-decoder network with attention that can be trained to convert a simulated document into a JSON string. In the documented experiment with this system, it achieved an accuracy of 99.99 percent on its simulated testing documents.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 25, 2023
Accession Number
AD1226944

Entities

People

  • Charles Norsworthy

Organizations

  • United States Naval Research Laboratory

Tags

Fields of Study

  • Computer science

Readers

  • Brain and Cognitive Science; Experimental Psychology; Cognitive Neuroscience
  • Computational Linguistics
  • Radio communications and signal processing.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Information Retrieval
  • AI & ML - Neural Networks