/gazette_extractor

Projekt Inżynierski 2016

Primary LanguagePython

Gazette Extractor

Authors:

Maximiliana Behnke

Sandra Ambroziak

Summary:

An experimental system that trains model to extract death notices from 20th century Polish newspapers.

It was created in cooperation with The Institute of Linguistics AMU.

Tools:

  • KenLM
  • Vowpal Wabbit
  • OpenCV
  • NLTK

Manual and tutorial:

http://gazette-extractor.readthedocs.io/