Better, faster, more: translation speed reality

5 06 2014

What are the mechanics of translation and how long does the full process take? While it has transformed from a discipline practiced by individual linguists and academics, into a hi-tech industry exponentially improved by specialized technology, translation still requires highly trained, multi-lingual human minds. And that means it takes time.

A person unfamiliar with the intricacies of translation might imagine that it occurs instantly as a translator reads a document, and then that translator only needs to get the new words down on paper or typed into a computer. But that scenario doesn’t resemble reality at all.

The following is a brief outline of what occurs (and excluding extra steps required by additional services such as DTP). To begin with, the project manager reads through a document and converts it to a versatile electronic file. She or he then runs it through a translation memory (TM) system to find passages already available in the target language (from past translations); gathers relevant dictionaries, subject matter references and style guides; a suitable specialized translator then translates “from scratch”, without machine translation, all text that was not available in TM; passes it along to another pair of trained eyes for editing and proofreading; and then it runs through quality assurance procedures. When the final copy is ready, the last step is to convert it into the format the client requires. If the translator is very familiar with the subject of the document, the translation process can take about one working day – eight hours – to complete between 2,000 and 3,000 words.

Some translators say they can translate over 4,000 or 5,000 words per day if the subject matter is well known to them, CAT tools are employed, and everything goes off without a hitch. But most estimate that the comfortable average for delivering accurate translations is closer to 2,000 words per day. Time for review (around 1,800 words per day) and for the pre-processing and quality assurance has to be added – so that for a 2,000 words translation you can count around 3 working days.

Many factors influence the length of time required for translations (in addition to subject familiarity and use of CAT tools):

  1. Complexity of the document subject, either technically or creatively (for example, “transcreation” of advertising can require hours of linguistic exploration to achieve culturally equivalent text).
  2. Format of the original – is it an electronic file or is it a hard copy, and if it’s a hard copy, is it clear?
  3. Repetitiveness of the text.
  4. Level of similarity between the source and target language.
  5. Final destination of the text: for internal use or publication.
  6. Who will put the finishing touches to the final copy, the translator or the client?

Professional LSP’s can assign multiple translators to a big project, of course, but the formula for estimating translation time must then include the hours required for assembling the whole, along with extra editing to ensure fluent tone and stylistic consistency.

What have you found to be the most troublesome obstacles to translation speed, and why is there so often high pressure to complete translations quickly?


 J. McShulskis


Machine Translation is not Google Translate

5 03 2014

Google Translate is one of the most popular instant translation systems available online, and while it is certainly a type of “machine translation,” it’s quite a different tool than those used in certain situations by professional language service providers (LSPs)such as Skrivanek.

google-translateTo generate translations, Google Translate (GT) searches millions of sentences for comparable patterns in origin- and target-language documents that have already been translated by human translators and entered into its database. Then, basically, it makes an “educated” guess as to what an appropriate translation would be. This process of seeking patterns in large amounts of text is called “statistical machine translation” (SMT).

You’ve probably seen how GT works: type in words and you will receive a quick translation (in any of 80 languages) that will range in quality from excellent to questionable, depending on how much text for your language pairing has been fed into the GT database. Google Translate director, German computer scientist Franz Josef Och, describes the GT process as the computation of “probabilities of translation” through comparison of the submitted text with billions of words of “learned” text in GT. The more text is available in the database, the “smarter” GT becomes. Tellingly, the GT creative team is made up of mathematicians and programmers and does not include any linguists.*

On the other hand, software systems such as PROMT, Asia Online, SYSTRAN and Moses, referred to as Machine Translation (MT), are complex, customizable translation engines that are specifically trained for certain projects or content in order to maximize efficiency and accuracy. Often used for technical and repetitive texts without subtleties, MT can assist large corporations in the translation of materials they simply would not have the capacity or budget for otherwise.

In the past MT systems were often entirely “rules based” (RBMT), meaning that information about language structures – not mathematical formulas – formed the foundation of their programming. Now MT engines like those mentioned above are often hybrid systems that combine RBMT and SMT. Basically, MT engineers “train” the sophisticated MT programs with glossaries from relevant fields, along with text from specific documents and corrections from previous mistakes, resulting in a tool that becomes more refined the more it is used for each client. This kind of multi-faceted MT requires extremely high levels of capital investment for both hardware and software, and for the process of customization.

Instant online translation tools like Google Translate are a gift in an era of communication expansion so extensive that a large American corporation might want immediate access to comments tweeted by an Icelandic teenager about its latest product. There are numerous instances of such social and commercial interaction online when communication speed is more important than language precision.

But for linguistically and culturally accurate translations of text that contains any ambiguities, nuances or critical information, hands-on human intelligence is still essential. Even complex MT systems are most appropriate for only some types of texts and then merely as producers of raw output that is checked, smoothed and corrected by human post-editors.

For further information:

*”Google Translate Has Ambitious Goals for Machine Translation,” by Thomas Schulz, Spiegel Online,, September 2013

J. McShulskis