Grammarly is an American cloud-based typing assistant. It offers a paid subscription for additional features and access to its translation application programming interface. Its algorithm uses convolutional neural networks and an English pivot. It initially offered translations between seven European languages and was gradually expanded to support 31 languages. The translating system was first developed within Linguee and launched as entity DeepL. Of course, the English wasn't perfect, but it made a tremendous contribution toward getting a handle on what was happening in the medieval Chinese text that had seldom been read by anyone (it was lost for more than a thousand years) and had never been translated into any other language beside Dutch.ĭeepL Translator is a neural machine translation service launched in August 2017 and owned by Cologne based DeepL SE. When I read the resulting English translation, I was amazed at how faithfully the English conveyed the sense and the feeling of the extremely recondite medieval Chinese text.
The Dutch translator had done a commendable job of getting from the difficult Chinese to Dutch, but then we had to use OCR on his limited circulation Dutch publication to produce a document to feed into DeepL. Specifically, what impressed me so much about DeepL in this instance is that we were faced with a Dutch translation of a rare, medieval Chinese text with a lot of esoteric vocabulary. Lately I myself have noticed that when I write papers, essays, and letters in word processing programs (e.g., Microsoft Word), the processor gives me mostly good suggestions for getting rid of superfluous, redundant, awkward suggestions. Many of them also use Grammarly to improve the quality of their writing. The scanned texts they use can then be fed into various applications for translation. They also mentioned that they use OCR apps on their phones. Most of the participants in my Middle Vernacular Sinitic (MVS) seminar (all attendees are from China, Japan, and Korea), said that they've been using it regularly for years. Seeing what DeepL could do, I was simply overwhelmed. In truth, we've barely mentioned DeepL before (see comments here, here, here, and here), so I really didn't notice it until this past week when my students and auditors from East Asia told me about it. Since we've been discussing phenomenal developments in AI quite a bit lately (see also under "Selected readings" below), now seems as good a time as any to introduce DeepL to the collective Language Log readership. As with other translators, it is subject to errors, but even so, DeepL remains one of the most accurate online translation tools that exits today.I have often sung the praises of Google Translate (see "Selected readings" below for a few sample posts), but now I've learned about an online translator that, for many languages, may be even better. The main limitation when using DeepL is that it only supports eight languages: Spanish, English, German, Portuguese, Italian, Dutch, Polish and Russian.ĭeepL is an incredibly useful tool for quick translations that provides excellent results for any content. Instead, the instant you hit Ctrl+C, the program opens up all by itself, even if it's closed. This way, you don't have to waste time opening the program and copying and pasting the text yourself. Then, the box located just below will show you the translation in the language entered.ĭeepL is designed so that all you have to do is select the text you want to translate and hit Ctrl+C twice on the keyboard for the text to automatically be copied and pasted in the program. To translate any text all you have to do is enter the text you want to translate in the first box, along with the language you want to translate it to. Even though it's still under development, it offers excellent results. The main reason for its accuracy is that it uses this technology together with its own dictionary, analyzing the context of the text itself to translate it accurately. DeepL is an online translator that's capable of analyzing text using neural networks.
0 kommentar(er)
