Artificial Intelligence and deep neural networks
applied to language processing

Neural Machine Translation (NMT):
let's go back to the origins

We have all heard of deep learning and artificial neural networks and have likely used solutions based on this technology such as image recognition, big data analysis and digital assistants that Web giants have integrated into their services.

In the last two years, much research has been conducting on applying artificial neural networks to natural language processing. Results are shared among an open source community in which SYSTRAN actively participates and shares its know-how.

A self-learning translation machine

As opposed to the current engines on the market (statistical and rule-based), a neural engine models the entire process of machine translation through a unique artificial neural network.

An Artificial Neural Network (ANN) is composed of layers of artificial neurons, the layers are connected together with weights called the parameters of the network.
A key element of neural network is in its ability to automatically correct its parameters during the training phase (few weeks). Technically, the generated output is compared to expected reference and corrective feedback sent "backward" to adjust weights and tune the network connections.

This technology which is based on complex algorithms at the forefront of Deep Learning, enables the PNMT™ (Pure Neural™ Machine Translation) engine to learn, generate the rules of a language from a given translated text and produce a translation overachieving the current state of the art and better than a non-native speaker.

Request a demo

Some fields are required

We respect your privacy, and will use this information only for contact purposes.

Helping companies succeed in the age of real-time

In the digital age, language barriers have, until now, represented one of the biggest challenges to rapid deployment of business strategies among global markets. Businesses now have the opportunity to explore new prospects thanks to advances in artificial intelligence and machine translation R&D.

With this highly innovative solution, SYSTRAN continues its quest for technological excellence in order to help companies succeed in the age of real-time, 24/7 global communication. SYSTRAN offers organizations access to the best translation quality on the market, closer than ever to human fluency and adapted to the specific contexts of each customer, ranging from the legal and automotive industry to IT and tourism.

Companies can deploy their business strategy in several countries at the same time, breaking down the language barrier and bringing out phenomenal gains in terms of time to market and productivity.


SYSTRAN testimonials

« The new PNMT™ technology offers unmatched translation quality and fluidity in the history of automatic translation. There are still areas of improvement on which R&D teams are already working. This technology will undoubtedly open up new perspectives for translators and contributors in a globalized world. »

CrosslangHeidi Depraetere, founder of Crosslang

« PNMT™ technology provided by SYSTRAN is a new step for human communication in general, and for tourism in particular. It brings a magnificent field of opportunities, new experiences and is an exciting linguistic journey! Augmented Tourist 2.0 is ReadyToGo. »

Petit FutéDominique Auzias, founder of Petit Futé

« Mostly the SYSTRAN PNMT™ engine understood what I wanted to say, and translated it very fluidly. For the most part, the terminology was spot on, and the sentences, well, they sounded human. »

LexceleraLori Thicke, the CEO of Lexcelera

With specialization, the potential of PNMT™ is highly enhanced

With its new PNMT™ engine, SYSTRAN can optimize neural networks in a post-training process called specialization. This method significantly improves the quality of translation in record time.

« Adapting translation to a specific domain such as legal, marketing, technical, pharmaceutical, is an absolute necessity for global companies and organizations. Offering professionals specialized translation solutions in their trade terminology has been part of SYSTRAN's DNA for many years. The generation of neural engines offers new capabilities in domain adaptation. PNMT™ is able to adapt a generic model to new data and even to each translator. Generic NMT is undoubtedly a great improvement in translation technology, but Specialized NMT is the technology that will truly help companies meet their global challenges. »

Jean Senellart, CEO of SYSTRAN


Some fields are required

We respect your privacy, and will use this information only for contact purposes.