Automated Analysis of Language Style and Structure in Technical and Other Documents.

Abstract

The project concerned with automated analysis of language style and structure in technical and other documents has had four primary emphases during the 1970-71 research year. One emphasis was the development of approaches to the modeling of thesauri, so that existing thesauri can be precisely described and new thesauri (more adequate to a wide range of information retrieval requirements) can be developed. A second emphasis was the writing of statistical data-gathering programs and the testing of statistical analytical tools on that data; this work is directed toward a statistical support package for natural language research. A third emphasis was upon beginning the development of a theory of prefixing in English in order to provide a basis for automated handling of prefixes. The fourth emphasis was upon programming a FORTRAN IV, Honeywell 635 version of the list-structure VIA programs, which are used for content analysis as well as for inputs to the research on thesauri and statistical analysis. (Author)

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1971
Accession Number
AD0735134

Entities

People

  • Sally Yeates Sedelow

Organizations

  • University of Kansas

Tags

Communities of Interest

  • Engineered Resilient Systems

DTIC Thesaurus Topics

  • Computer Programming
  • Computing-Related Activities
  • Data Science
  • Information Retrieval
  • Information Science
  • Language
  • Natural Languages
  • Statistical Analysis
  • Statistical Data
  • Thesauri
  • Words (Language)

Readers

  • Business Analytics
  • Computational Linguistics
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation