Four Common Steps of an MTPE Workflow Nimdzi Finger Food
How does one implement Machine Translation (MT) in their lives?
Here’s a general approach to MT selection which we mentioned before:
Looks good and clear. But let’s dig further into how this nice scheme can be applied to a Machine Translation Post Editing (MTPE) workflow. Here’s a common 4-step way:
- Preparation:
- Preparing the source data to train the engine
- Evaluating the market of best MT engines for your language pair
- Selecting engines for testing
- Testing and QA, which is normally done with the help of MT providers or external MT consultants
- Actual post-editing, which includes collecting feedback from translators on MT output quality
- Further QA, with evaluating the results and possibly retraining the engine
Then, depending on the project size, there may be variations:
| Small PEMT projects | Medium projects / MT as a first step | Major projects / MT only |
|---|---|---|
|
1. Prepare a set of segments for evaluation (about 1,500-2,000) |
1. Make a comparison of the basic stock engines: determine which maximum quality of translations can be obtained without training engines |
| 2. Select 4-5 engines to evaluate |
2. Prepare a list of stock engines for quality assessment per language pair |
2. Prepare a glossary of terms/phrases and a corpus for training (~10,000+ segments) |
|
3a. Plug the engines into a CAT tool |
3. Translate the test set of segments |
3. Train suitable domain adaptive engines |
|
3b. Translate materials through selected 4-5 engines and load into your CAT tool |
4. Calculate automatic reference-based coefficients |
4. Evaluate the quality of trained engines and compare with the base stock models  |
| 4. Choose the best option during translation | 5. Compare the best engines according to the results of the coefficients and quality |
5. When you collect feedback from translators on quality, re-train your favorite engines and evaluate quality again  |
| Â | 6. Try translating through the winning engine |
 |
See also the state of MT by Intento for an in-depth guide on what solutions there are on the market.
So, you now have a workflow diagram, four steps, and three detailed scenarios to sprinkle a little bit of MTPE in your life. Whichever path you select, may the force be with you!
Nimdzi Finger Food is the bite-sized insight you need to fuel your decision-making today.
Stay up to date as Nimdzi publishes new insights. We will keep you posted as each new report is published so that you are sure not to miss anything.
