| H-1173 Budapest, Pesti út 8-12.,
| Phone: +36 (1) 202-0202, +36 (1) 224-0920 | E-mail: multi@lingua.hu
  
  

Our latest news




Preparing for Machine Translation: What Machines Can and Can`t Do

There is nothing especially novel about machine translation, a technology that reaches back to 1951, when a team from IBM and Georgetown University first demonstrated a computer’s ability to translate short phrases from English into Russian. In 63 years, the machines involved in machine translation have evolved. What a warehouse-sized computer could do in 1951, a laptop can do even better today.



If your business is ready to enter the multilingual world, machine translation might offer the short-term solution you need to get your essential materials in front of customers, partners, and suppliers. If you’re preparing to translate your documents, you’ll want to begin thinking about how to prepare your literature for a computer to read. Translation machines are smart, but they’re not that smart, and there are some tricks to making the process work as efficiently as possible.

Good translation starts with massive information:
Decades ago, programmers tried to cram artificial translation brains full of vocabulary, grammar, and syntax so that a source document could be rendered in a target language as a matter of simple substitution. But that tactic has changed. We don’t master a language by first learning all the rules. We learn by inculcating some very general rules and then refining them as we go along. So too do today’s intelligent machines. Today we know that machines, like humans, learn best through millions of small inputs.
If you’re approaching machine translation for the first time, more is better. The machine can learn best if it has massive amounts of data to begin with. The machine will do a better job getting your language right if it can work with the same subject over and over, building upon what it takes from a massive source of basic information.

Write clearly and directly:
If you’re writing for native English speakers, rhetorical flourish and literary style can add value. If you’re writing for a machine, style conventions should conform to the principle that a direct approach is best. The major theme of your business voice for this process should be your specific business objective.
Be certain that your content is free of spelling and grammar errors and make sure your meaning is fully expressed in clear terms. Even the smartest machines cannot grasp overall meaning the way human beings do as a matter of routine. The machine will be more successful translating material that is written in the same style and voice consistently than trying to reason through the diverse voices of multiple writers.

Formatting your files:
When you’re satisfied that the phrasing you used is clear and direct enough, you’ll also want to make sure it is formatted so the machine can recognize it. The best translation will come from content organized in sentences and paragraphs, free of text formatting that can bewilder an artificial brain. Don’t ask your machine translator to deal with embedded images. Avoid sentence fragments. Remove tables and images, targets, citations, tables of contents, and so on.

Quality input equals quality output:
No machine is Steinbeck. None ever will be. Thus no machine translation can or will be any better than the content one puts into it. Taking the time to make your original text the best that it can be will have direct results for the quality of your translation. Still, even the best content and the most sophisticated translation processor will result in an imperfect translation.
So while it is a good idea to begin with the best text possible, the best use of machine translation still includes a post-machine process: the use of human post-editors who are qualified writers in your target language. Where the machine gets close, human translators can hit the mark precisely.
Language is as much an art as it is a science. Real human language might always remain slightly outside the computer’s grasp. The tips above will help your company get the most out of this service. That alone will get you started, but the human touch will get you where you want to be: fluent and effective in a world rich with diversity and endowed with a language inventory more intricate and expressive than any machine intelligence could possibly describe, much less match.

Click here for more information.
Our latest news

Translation tech gets Olympic push

Japan may not be the best in the world when it comes to speaking English, but it remains a pioneer in developing cutting-edge translation technology.
With the 2020 Tokyo Olympics approaching, the nation is once again plotting to surprise the world, this time with high-quality, real-time machine translation systems.
Public and private institutions are working eagerly to develop and upgrade the technology so it can easily be used by tourists, whose numbers are growing sharply

Preparing for Machine Translation: What Machines Can and Can't Do

There is nothing especially novel about machine translation, a technology that reaches back to 1951, when a team from IBM and Georgetown University first demonstrated a computer’s ability to translate short phrases from English into Russian. In 63 years, the machines involved in machine translation have evolved. What a warehouse-sized computer could do in 1951, a laptop can do even better today.