Feature Overview

Analyse the quality of KantanMT using industry standards quality metrics

Measuring the performance of your KantanMT engine is where the art of Machine Translation meets the science of Machine Translation. It gives you the ability to prove the impact of your machine translation efforts - but only if you have an ability to measure from its initial build through its multiple re-trainings and production runs.

Often the problem isn't having too little measurement data; it's having too much or the wrong data!

KantanMT helps you easily track how your Machine Translation engines are contributing to the efficiency of your translation process with cutting edge analytics and reporting tools. Our platform puts the right metrics where you need them. Without requiring hours of number crunching.

KantanMT provides you with:

  • KantanBuildAnalytics™: BuildAnalytics helps analyse and track all your quality measurements for the lifetime of each KantanMT engine
  • Engine Fluency: Automatic BLEU score tracking and analysis to evaluate the fluency of your KantanMT engines
  • Engine Recall & Precision: The ability to determine the recall and precision of each KantanMT engine using F-Measure
  • Estimate Post-Editing Effort: An estimate of the post-editing effort for each engine using Translation Error Rate (TER) analysis.
  • Customised Test Data: Ability to upload your own pre-determined test data in order to provide a baseline for all quality measurements

Never get confused or lost in the data again. KantanMT gives you key reports that are useful right out-of-the box.

Here's what our members are saying:

Simplicity and flexibility made us choose KantanMT.

Teddy Bengtsson, Founder, RoundTable Studio

KantanMT has been used at UCL to teach students at master's level.

R.B. Pinero, Dr., UCL, London

Contact Us