Machine translation & AI quality
How this is scored
What the machine translation does and how well it is controlled: the languages and language pairs covered, the engine (own neural or LLM model, or a choice of third-party engines such as DeepL, Google, Microsoft or an LLM), glossaries and formality applied during translation, document translation that keeps the layout (Word, PowerPoint, PDF, InDesign), custom or adaptive models trained on the customer's own translations, automatic quality estimation or scoring, and published evaluations of translation quality.
0 — No machine translation of any kind, and no way to connect an engine.
3 — Machine translation is offered or one engine can be connected; languages, glossary use and quality controls are basic or not described.
5 — Machine translation for the major European and world languages with the list published, glossaries applied during translation, a formality or tone setting, document translation that keeps formatting for common office formats, and either an own engine or a choice of several named engines.
8 — Custom or adaptive models that learn from the customer's translation memory or corrections, automatic quality estimation per segment with a threshold that routes weak segments to human review, LLM-based translation with style guides and context, engine selection per language pair stated, and a published quality evaluation with its method.
10 — Translation quality that an organisation can measure and steer: evaluations against named benchmarks or blind human review published with their method, quality estimation calibrated and explained, custom models with their training data and isolation documented, and every machine-translated segment traceable to the engine, model version and glossary that produced it.
The In-House Document Translator
The captured pages show a genuine choice of more than twenty engines — DeepL, OpenAI, Anthropic Claude, Google Gemini among them — with automatic routing that picks the engine per language pair and content type, custom prompts that pull the customer's own translation memory and glossary in via retrieval, and quality estimation from either an LLM assessor or a fine-tuned XLM-R model, plus a published quality figure of MQM 98+ for their AI-powered human translation. Customers can also bring their own trained engines and their own model keys. I found no public information on document translation that keeps the layout of Word or PDF files, which is exactly what my contracts and operating manuals would need. 10 9 17 14 13