An Artificial Intelligence revolution that benefits DAT's customers

Three steps for a professional result

Having been at the forefront of the use of translation memories, DAT is naturally prepared for the integration of machine translation technologies based on neural networks and artificial intelligence in its process.
However, some clients remain focused on the setbacks of machine translation in its early stages. This was the period of Google Translate's anecdotal translations where machine translation systems were based on statistical models. But since then, things have changed enormously with the adoption of deep learning systems and neural networks.
To simplify, we will say that current systems no longer calculate but reason and therefore learn from their mistakes. And among the most valuable materials used to learn from, there are the translation memories (TMs) that DAT has accumulated for more than 20 years.
The schema becomes as follows:


Step 1: Pre-translation


  1. From the interface of the translation environment (as SDL Studio), the user enters the text to be translated and chooses the language and domain settings. From this same interface, the user also selects the relevant memories and connects them.
  2. The user also connects the automatic translation system API and initializes a pre-translation.
  3. At this stage, the output is a partial translation that reflects the content of the translation memories. And it is from there that the machine translation system (MT) takes over to complete the missing translations.

Step 2: Machine translation


  1. The machine translation system integrates the terminology and context of translations from translation memories into its process. It also stores them in the user's work instance. This is where some of the learning takes place.
  2. For segments that are not in translation memories, the system will use its neural networks and previous learnings to translate them itself.
  3. The output of this process is a raw translation where the segments translated by the machine are marked for the post-editing step.

Step 3: Human Post-editing


  1. The reviewer receives a pre-translation package and opens it in the interface where the segments from the memories and those from the MT system are clearly identified.
  2. He begins his post-editing work by being connected to the translation memories and the MT system. The two systems are enriched in parallel by the reviser corrections.
  3. The output is a revised translation, with enhanced memories and an up-to-date MT system.
    Among the advantages of this process is the absence of contradictions and errors in the figures, which is already considerable, especially for technical translations.
    This process allows clients to translate more documents more quickly, at lower cost and with professional quality. For example, it is estimated that the cost savings are in the range of 40 per cent for some documents and that the time savings are in the range of 60 per cent.
    It is not, however, applicable to all documents. The areas of exclusion are for example commercial brochures, websites, advertising and any documents that require transcreation rather than translation.
    However, it is extremely effective for all  manuals, maintenance manuals and technical specifications that require greater fidelity to the text.


From "Eureka" to "Attention is all you need"
The way to Artificial Intelligence