Questions and answers about personalized machine translation. I collected your questions throughout this series and present the answers here. If I missed something or if you have new questions, please ask.
A walk through six steps of personalized machine translation that I created 3 years ago reveals… how it sets up in minutes… how increased productivity monetizes your investment… and how to continue monetizing on autopilot — while you do the things you love doing.
“I’ve already tried to post-edit machine translation and it never worked!” Most of what you’re being told about machine translation and post-editing is flat out wrong. The biggest mistake people make when working with machine translation is believing the hype.
Let’s take a closer look at personalized machine translation. Personalized machine translation and the personal computer (PC) were breakthroughs because they put you in control. Ask yourself, which machine translation platforms put you in control to do things your way? That’s the power of personalization.
It’s easy to see that personalized machine translation transformed a customer’s career as a professional translator. From non-stop stress missing deadlines to calm assurance delivering her projects ahead of schedule, customers gave her more jobs, she made more money and she began living her dream.
I focus on productivity because productivity give you the time and opportunity to achieve your dreams. No matter what you believe about the value of machine translation for your business, personalized machine translation boosts productivity… if you know what you’re doing.
Machine translation (MT) technology has become a mainstream tool in the translation services market. Unfortunately, machine-translated segments are not created equal. Some are detrimental to a translator’s productivity. Therefore, a translator needs benchmarks that can predict, with a high degree of confidence, the likelihood that machine-translated segments from a given system will benefit his daily work productivity.
Igor Goldfarb’s shares his experience using Slate with patent translations for a year. He is one of the earliest Slate Desktop users. He’s been known to work with a timer next to his keyboard measuring how his personalized engine actually affects his productivity. Here’s what he says in Russian to his Russian colleagues that Slate and memoQ speed his work at least 30%. For a gist translation, our English readers can use the Google or you can read his English testimonial here: https://www.slate.rocks/igor-goldfarb/
This re-post also includes two appendices that made the article too long for Isabella’s blog. The first is a glossary of our score terms. The second shows twelve (12) example source-target segments plus the output translations from Isabella’s engine and Google.
Honest people are working hard to catch fake news with hands in the cookie jar. Fake news tells us that neural machine translation (NMT) is “Nearly Indistinguishable From Human Translation,” but honest people are working…
Continue reading →