New Translator Provides More Human-Like Translations

Germany-based startup DeepL launched a neural machine translator that was preferred by professional (human) translators by a 3-to-1 margin over similar tools.

The deep learning company claims “that (DeepL Translator) can boast the world’s most accurate and natural-sounding machine translation tool. When users enter a text, DeepL’s artificial intelligence is able to capture even the slightest nuances and reproduce them in translation unlike any other service.”

“We have achieved several significant improvements in neural network architecture,” says Gereon Frahling, the company’s founder and CEO who previously worked at Google Research. “By arranging the neurons and their connections differently, we have enabled our networks to map natural language more comprehensively than any other neural network to date.”

The machine translator system was trained with the cuDNN-accelerated TensorFlow deep learning framework on a 5.1-petaflop supercomputer equipped with Tesla P100 and GTX 1080 Ti GPUs – the company says the system would be ranked number 23 on the TOP500 list, and has enough power to translate a million words in under a second.

For the networks to understand a multitude of translations and learn independently how to translate with correct grammar and structure, the team trained their neural translation networks on a huge collection of multilingual texts.

“Due to the abundance of renewable energy, we can train our neural networks very cost-efficiently in Iceland. We will continue to invest in high-performance hardware,” explains CTO Jaroslaw Kutylowski.

DeepL Translator supports over 40 language combinations between English, German, French, Spanish, Italian, Polish, and Dutch. The neural networks are already training to master more languages like Mandarin, Japanese, and Russian.

Read more >

About Brad Nemire

Brad Nemire
Brad Nemire is on the Developer Marketing team and loves reading about all of the fascinating research being done by developers using NVIDIA GPUs. Reach out to Brad on Twitter @BradNemire and let him know how you’re using GPUs to accelerate your research. Brad graduated from San Diego State University and currently resides in San Jose, CA. Follow @BradNemire on Twitter