Language assets
Translation memory
Save approved source and target segments, reuse exact matches, and review fuzzy matches when similar text appears.
A translation memory (TM) is a database of segment pairs: source text and the translation you approved for it. When new text arrives, in the translator or in a document, DeepReference checks the TM first. Exact repetitions are filled from memory; similar segments surface as fuzzy matches in the editor for you to accept or adapt. Part of the Translation Memory workflow (Translator Pro and up).
How your TM fills up
- Approving segments in either editor stores the pair. This is the main path, and it means your TM is made of translations a human signed off on.
- Importing TMX files brings in memories exported by common CAT tools. You can also export the memory to TMX for use elsewhere.
- Entries carry their language pair, domain, and source document, so lookups stay relevant.
Match types in the editor
| Match | Meaning |
|---|---|
| 100% | The exact same source text was translated before. One click applies it, or turn on auto-apply in the editor. |
| Fuzzy (75-99%) | A similar segment exists. The panel shows the stored pair and the score; you adapt it rather than translating from zero. |
| New | Nothing similar in memory; the model translates it fresh. |
Managing your TM
Language assets → Translation memory lists saved segments with search and filters. Edit or delete an entry when its target text is outdated or wrong. Concordance search searches the same data from inside either editor.
Two related settings live in CAT settings: auto-apply 100% matches (insert exact matches automatically instead of just suggesting them) and the consistency lock (an identical source segment always gets the identical target, everywhere).
Multiple memories and termbases (teams)
Business and Enterprise plans can keep several named translation memories and termbases. Create or rename a container in Language assets, mark one active for new approvals, and assign existing segments by language pair or domain. The same controls are available for termbases.
Separate memories are useful when work for different clients must not share approved phrasing. Select the correct active container before approving segments for a new job.
When memory changes the job
An exact match can use the target text that was approved earlier instead of generating another version. A fuzzy match is offered as a reference and still needs review. Run the Analysis report before a job to see how much source text falls into each match band.
Keep exploring
Analysis report
See the source-word total, internal repetitions, translation-memory coverage, and a transparent workload estimate before you begin a job.
Concordance search
Search Translation Memory for a word or phrase and review the source and target segments where it appeared.
Translation editor
Review source and target segments side by side with Translation Memory, terminology, QA, comments, status, and per-segment retranslation.
Glossary
Store approved term pairs for a language pair and apply them during text translation, document translation, and review.