After 10 years since its launch, when it revolutionized the translator software market, this week Google Translator finally received a significant update.
Until now, Google Translator was only accurate with isolated words, and what was seen in sentence translations were confusing and inconsistent results. This was because the system always translated words individually and only then organized them in a way that made sense, which in practice did not actually happen. However, with the new update, this problem may have come to an end.
With the new update, the Translator gained neural networks, a feature that allows Google to decipher entire sentences at once. As a result, the translation becomes more fluent and acquires greater fidelity to the original sentence, especially because neural networks enable a reading that takes into account the context of the content. The Translator reads the sentences and presents the result according to the information contained in the entire paragraph, which did not happen in the previous version.
According to Google, this change in the reading method makes the results much more natural for native speakers of certain languages, and with it, translation errors should initially decrease by up to 60%. This number is expected to reduce even further over time, as in neural networks, the system continuously improves based on user interactions.
The new Google Translator is already available on the company's official website and in apps for Android and iOS systems, but for now, it only supports eight languages: Portuguese, English, French, German, Spanish, Chinese, Japanese, Korean, and Turkish. This corresponds to only 35% of the requests made to the system within the 103 supported languages.
The expectation is that soon the new feature will be released for all other languages.