You may know this as LQA, linguistic quality assurance, Auto LQA, linguistic QC, language quality review, or MQM, DQF-MQM and J2450 scoring.
What you get
A report, not a corrected file. If you want the file corrected, that is post-editing and it is priced differently.
The report contains four things:
- A headline number — penalty points per 1,000 words, against a threshold agreed with you before we start.
- A classified error list — every error given a type and a severity, with location, source text, target text and a comment.
- A breakdown by error type, so you can see whether you have an accuracy problem, a terminology problem or a register problem. They have different fixes.
- The pattern. Two or three sentences on what the errors have in common, and what would stop them recurring — a glossary entry, a prompt change, a different threshold.
That last section is the one we would ask you to read first. A list of errors tells you what went wrong once. The pattern tells you how to stop it happening across the rest of the set.
We score against MQM error categories and severity levels, and work in DQF-MQM or, in automotive, J2450 where that is your framework rather than ours. The method is set out in full on how we score, including the severity weights, the arithmetic, and the thresholds we would suggest for different kinds of content.
What it is for
Three situations, in our experience:
- You need to know whether an engine, a vendor or an internal team is producing machine or human output good enough to publish, and you need the answer in a form you can show someone else.
- Your automated checks have flagged a body of work and you need a qualified human assessment of it, not another model's opinion.
- You are in a regulated sector, and the evidence that review happened is itself part of what you are delivering.
How we work with automated checks
We assume they exist, and we are built to sit at the end of them. Where we think a threshold is set wrong, we will say so — which is a conversation the party that configured the threshold cannot easily have with you.
Comparing engines and vendors
The same review method, run comparatively: your current engine against alternatives, or one vendor against another, on your own content rather than on a benchmark. No single engine wins everywhere — published comparisons show different engines winning different languages, with gaps between the best and second-best choice large enough to decide whether output is publishable. Most buyers standardised on one engine and have never re-checked. That work has its own page: Engine Fitness Report.
Independence
We do not sell a translation engine and we do not sell a platform. On the work we review, we were not the producer.
We do not independently assess output we produced ourselves. Where we have translated or post-edited a file, the impartial review of it has to come from somebody else.
What it costs
Per hour, or per sample of an agreed size. Never per word.
Delivered, or staffed
Send us the work and we return the deliverable described above. Or place our reviewers into your own process and tooling and run them under your rubric, your schema and your brand. Same people, same documentation, different contract. Tell us which you want and we will price it that way.
Need decisions on specific flagged segments rather than a report on a body of work? That is Exception Review.
Common questions
How is this different from proofreading?
Proofreading produces a corrected file. This produces a categorised, scored assessment - what was wrong, what type of error it was, how severe, and what that means for whether the content can be released. You can buy the corrections as well, but the report is the deliverable.
Will you review work produced by another supplier?
Yes. That is most of what this service is for. We assess the output on its merits and we have no relationship with whoever produced it.
Do you sample or check everything?
Both are available. Sampling is right for ongoing supplier monitoring; full review is right for release-critical content. We will tell you which one your content justifies rather than selling you the larger number.
What framework do you score against?
MQM by default, because it is the industry standard and your clients will recognise it. We can work to DQF-MQM, to J2450 for automotive, or to a client's own scorecard if one already exists.