Skip to content

gitgetgotgotten/transition-extractor

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

5 Commits
Β 
Β 
Β 
Β 

Repository files navigation

πŸ“ Transition Phrase Extractor

This Streamlit app extracts structured transition phrase triplets from .docx files containing regional French news articles.

Each triplet is formatted as:

  • paragraph_a: text before the transition
  • transition: the linking phrase (e.g., "Dans un tout autre registre")
  • paragraph_b: text after the transition

πŸ”§ Installation

pip install streamlit python-docx

streamlit run transition_extractor.py

About

Transition Extractor for News Articles

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages