Skip to content

Analyse Post-Edit density data to create post-processing rules

License

Notifications You must be signed in to change notification settings

SeeligA/ped_reader

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PED Reader and PED Writer Notebooks

Two interactive notebooks to analyze and improve machine translation output.

How are these resources useful?

The Reader notebook uses the post-edit density metric for analyzing and comparing productivity rates across vendors, languages and projects. It can be used on its own or as a reporting solution for the Woerdle-zehla tool. The notebook helps you to address frequent errors and mistranslation in your MT output in a statistically significant way.

The Writer notebook translates analysis into action. Decrease post-editing efforts by applying search and replace actions directly to your XLIFF files.

Features:

  • Interactive controls for viewing, filtering and visualizing PED data
  • Advanced search & replace functions for date formatting, casing and tags.
  • Sample data and replacement rules to get you started.

Use cases for translation services:

  • Creating vendor reports based on PED data
  • Analyzing MT potential across languages
  • Reducing post-editing efforts through search & replace automation

Requirements

If you are using Anaconda as a package manager, no additional libraries are required. Just make sure that the source modules are in your path.

Questions

Feel free to drop me a line in case of any questions.

Releases

No releases published

Packages

No packages published