As someone who lives between two countries, I’ve relied heavily on machine translation for a number of years. It took me years before I could communicate casually with my in-laws (they’re fluent in German and Polish, but not English), without my wife serving as an interpreter. (I don’t need to tell you how dangerous that can be.)
I realize that nothing beats a skilled human translator. But who has time (or money) to hire a person to translate simple, everyday tasks?
That’s why I’ve always been amazed at computer-aided translation, specifically Google Translate.
True, in its earlier days, Google Translate could spit out some pretty laughable, if not completely unintelligible, nonsense in an attempt to convert a message from one language to another. But generally, most of its attempts were helpful.
In recent times, I noticed the quality of these translations steadily improving. Nowadays, I can literally copy and paste a pretty advanced technical document (or God forbid, a letter written in German legalese), and the translation is remarkably good–at least as good as a human translator’s first draft.
Google is consistently at the head of the pack when it comes to A.I. and algorithm-based learning, and Translate’s no exception. The program generates translations using patterns found in huge amounts of text, discovered through millions of documents that have already been translated by humans. As time goes on, the program recognizes more and more patterns, receives input from real people, and continues to refine its translations.
Then, recently, something really exciting happened.
As reported by technology blog Tech2:
“In September, Google switched from Phrase-Based Machine Translation (PBMT) to Google Neural Machine Translation (GNMT) for handling translations between Chinese and English. The Chinese and English language pair has historically been difficult for machines to translate, and Google managed to get its system close to human levels of translation by using bilingual people to train the system … Google planned to add GNMT for all 103 languages in Google Translate. That would mean feeding in data for 103^2 language pairs, and the artificial intelligence would have to handle 10,609 models.
Google tackled this problem by allowing a single system to translate between multiple languages … When the translation knowledge was shared, curious Google engineers checked if the A.I. could translate between language pairs it was not explicitly trained on before. This was the first time machine based translation has successfully translated sentences using knowledge gained from training to translate other languages.”
In other words, Google Translate’s A.I. actually created its own language, to enable it to better translate other languages.
So, when was the last time you used Google Translate? If it’s been a while, I suggest you give it another try.
Because those results aren’t as funny as they used to be, but they’re a lot more useful.