When you set up pretranslation, the system inserts TM matches and machine translation into the text before the work is started. This significantly speeds up the translation process, because the translator will not have to copy translation memory matches or machine translation into each segment manually.
Let’s suppose you have enabled on the project both a TM that has already been used to record translations, and machine translation.
Now, on the Settings page, click the Workflow Stages switch and open the Pretranslation tab.
Inserting numbers from the source
If your text contains a lot of numbers, click Source (Numbers Only) so that all the segments containing only numbers are copied to the translation). Decimal and thousand separators in this case will be converted to match the norms of the target language.
You can specify that the system must confirm such segments right away.
The rule for inserting numbers is automatically executed first.
Inserting translation memory matches
Press Add Rule.
Click Translation Memory.
Select which TM you want to use from the ones you have enabled on the project.
In the field Insert if a match is no less than specify the minimum percentage of coincidence between a segment in the document and the translation memory at which the system must insert a translation from the TM.
You can also specify the minimum length of a segment (in words) at which the matches must be inserted using the Insert if a segment has no fewer words than field.
Finally, specify in the Confirm segments field if the system should confirm the inserted translations.
If you are sure of the quality of the translations in the selected TM and have set the minimum match percentage at 100%, you can specify that the system must confirm such matches. If you have doubts about the quality of the TM or have set the match threshold below 100%, you are better off not specifying automatic confirmation of such matches. In this case matches will be inserted, but the translator will check them, making corrections if necessary, and then manually confirming them.
By the same token, you can set up rules for each TM in a project (if there is more than one). The rules are executed one after the other; therefore you should set up rules whereby matches from the most reliable translation memory are inserted first.
You can set up more than one rule for each TM: for example, you can have Smartcat first insert 100% matches and confirm them, and then insert matches that are 75% and up, but without confirmation.
Inserting machine translation output
To use the machine translation function to fill all segments for which no matches have been found in the translation memory, press Add Rule.
Click Machine Translation.
Specify if you want the system to confirm segments containing machine translation. In most cases, these segments should not be automatically confirmed, because segments containing machine translation require corrections.
During pretranslation, the insertion of machine translation is executed after the other rules.
You can set up and run pretranslation later, but keep in mind that it will only be applied to those segments that have not yet been translated.
After configuring pretranslation, press the Finish button.