A spin-off of the Hieronymus agency, which specialises in legal and financial translation, Neur.on is breaking new ground with Corrext, a machine translation platform based on Natural Language Processing (NLP). A major challenge in a world where data security is key and terminology extremely complex. Neur.on is a success story that is as much about technology as it is about people.
Hieronymus, an agency which specialises in legal and financial translation, embarked on the AI adventure following an initial Innosuisse project supported by Alliance, which introduced them to the potential of data and Natural Language Processing (NLP). Paula Reichenberg, director of Hieronymus, decided to create Neur.on, a spin-off dedicated to neural machine translation for legal and financial professionals. This LegalTech startup surrounded itself with the right people to take on major challenges, and launched the Corrext platform, which optimises translation processes for complex documents, while ensuring quality, expertise and security.
Transforming a Traditional Profession
Following the emergence and widespread adoption of neural machine translation solutions, Hieronymus came up with the idea of taking another crucial step towards automation. “We discovered it was also possible to automate the preparatory phase of translations — from identifying lexical fields to checking formats — while ensuring maximum data security,” explains Paula Reichenberg. But the challenge is significant: entering a complex technical world, while ensuring seamless integration with the highly specific needs of legal and financial translation. Artificial intelligence must therefore assist legal specialists in a controlled environment, where each document is analysed and adapted according to precise criteria, with human intervention to validate technical and sensitive passages.
From the Innosuisse Project to the Birth of a Startup
While Paula Reichenberg was convinced she should open up her SME to the world of data, she needed someone to bridge the gap between the legal world and the scientific and technical world. It was during a class at EPFL that she heard about Alliance and Robert van Kommer, ICT innovation mentor. “From the very first contact, Robert was able to understand our needs and pointed us in the right direction.” He connected her to Jean Hennebert, from iCoSys Institute at HEIA-FR (Fribourg School of Engineering and Architecture), and supported the first Innosuisse project, which was approved. Paula Reichenberg then decided to start a second Innosuisse project, again with the support of Robert van Kommer, to create the startup Neur.on. This was followed by a third SIP project, for which Robert van Kommer acted as consultant. “These Innosuisse projects require a lot of hard work, rigor and collaboration. Robert’s help allowed us to make great strides, and the story doesn’t end there,” confides Paula Reichenberg.
Putting together a strong Innosuisse proposal requires not only a great rigor, but above all close collaboration and genuine trust among everyone on the team. You can’t do it alone.
NLP in the Service of Human Expertise
With Corrext, Neur.on designed a disruptive platform for the legal translation market. The platform’s innovation lies not only in its use of NLP to automate translations, but above all in the support it offers users. “Contrary to what you might think, machine translation has not made the profession of translator obsolete — quite the opposite,” emphasises Paula Reichenberg. The platform developed by Neur.on identifies the most complex passages, pinpoints sector-specific vocabulary and generates a reliability score for each part of the text. This assistant function guides users to the elements requiring manual verification, and goes far beyond standard tools, while ensuring strict control of data security.
Collaboration: the Key to Success
Today, Neur.on continues to innovate with a reinforced team. The startup is in product-market fit phase and making rapid progress. The Innosuisse proposals developed with HEIA-FR and the support of Alliance enabled them to establish clear objectives, that still serve as their roadmap today. Research is progressing, the product is evolving, and several students who worked on the projects have been hired, creating a diverse team of linguists, lawyers and engineers, all of whom are deeply committed.
Camille Pousin, 1 October 2024.