NTT Data: Description of the Erie System used for MUC-6

Abstract

Erie is a name recognition system developed for the Multilingual Entity Task (MET) in MUC-6. The pattern matching engine recognizes organization, person, and place names along with time and numeric expressions in Japanese text. Although our previous information extraction system Textract performed well in MUC-5, the pattern matching engine, which was written in AWK language, was slow[2). System maintenance was also difficult, since the patterns were defined in both the matching engine and the pattern files. Erie solves these problems by generating a pattern matching engine in C language directly from the defined patterns.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 1996
Accession Number
ADA631831

Entities

People

  • Tsuyoshi Kitani
  • Yoshio Eriguchi

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Accuracy
  • Boundaries
  • Computer Vision
  • Corporations
  • Dictionaries
  • Digital Communications
  • Electronic Mail
  • Generators
  • Governments
  • Image Processing
  • Information Operations
  • Language
  • Newspapers
  • Personality
  • Recognition

Fields of Study

  • Computer science

Readers

  • Coastal and Marine Engineering/Sediment Transport/Hydraulic Engineering
  • Computational Linguistics

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval