Digital Grammars
Language technology to rely on.

Enabling reliable communication where it matters.

Patient-centered care

Empower patients by facilitating communication with health care workers, even when they don't speak the same language.

Safe and equal treatment for all

High-quality verified translations lead to improved care for all patients, no matter what language they speak.

Fully dependable and always available

Translation at your fingertips whenever you need it, without waiting for an interpreter. Our app knows millions of phrases, with support for both text and speech.

From data to language and back again.

Make your formal languages accessible to everyone

Conversion of formal specifications and source code to human-readable natural language texts, automatically and reversibly.

Instantly multilingual product descriptions

Keep your documentation up to date in all languages by generating it directly from your data. Provide question answering and reasoning in your customers' own language, without maintaining translations.

Standardise communication with Controlled Natural Language

CNLs such as Simplified Technical English promote global collaboration by providing a common working language. Boost this potential with intelligent teaching tools, semantic analysis, and multilinguality.

archTrackingData!? = nil ⇒ wsInProcessUnit′ = wsInProcessUnit
archTrackingData!? ≠ nil
  ∧ (the archTrackingData!?).trackUnit = undefinedUnitId ⇒
  wsInProcessUnit′ = {order!?} ⩤ wsInProcessUnit
archTrackingData!? ≠ nil
  ∧ (the archTrackingData!?).trackUnit ≠ undefinedUnitId ⇒
  wsInProcessUnit′ = wsInProcessUnit ⊕
  {order!? ↦ (the archTrackingData!?).trackUnit}
Specification expressed in formal language

If the tracking data is not available, then the unit in process will not change.

If the tracking data is available, then

  • if the track unit is undefined, then this order is removed from the set of orders in process.
  • if the track unit is well-defined, then the order is related to the track unit in the set of orders in process.
The same specification rendered in natural language

Get in touch.

Send us an email

What makes us different

Most other language technology companies are based on machine learning, human translators, or some combination of the two. But our technology is completely machine-based without being vulnerable to the unpredictability of learned systems. Our products are hand-crafted to be specialised, precise, and reliable, while remaining explainable, fast, and always available. What makes us unique is our ability to offer all of these characteristics together in an integrated solution.


By building systems which are tailored to a specific context and application, we can deliver higher quality translations which use domain terminology correctly and consistently.


Unlike black-box methods such as machine learning, our technology is fully transparent and verifiable. We not only provide the what but also the how and why.


Our technology is not brittle to minor changes in input or biased by any training data. Every translation we produce is the result of verified rules conformant with your specific application.


We are ready to target over 30 languages, and are able to scale up to any number of languages with a minimum increase in overhead.


We combine the quality and reliability of a human translator with the speed and constant availability of a web service, mobile app, or standalone program.


Other machine translation systems cannot be trusted with mission-critical information. Our solutions are for producer-level translation, where quality cannot be left to chance.

How it works

The variation that exists across different natural languages is vast. But meaning is universal. Instead of managing translations between countless language pairs, our approach to multilinguality is based on capturing semantic meaning in a language-independent way. This makes us scalable, avoids the need for extensive training data, and ensures that meaning is never lost in translation.

Our interactive demo below shows a semantic structure, displayed here as a tree, together with concrete linearisations of it in a number of different natural languages. See what happens when you hover and click around the nodes and words! As the tree changes, all linearisations in all languages are instantly updated and all translations are kept in sync.

Learn more about our technologies


Västra gotalandsregionenAltranTextualSignatuSU Ambulans

Lex Cogitans


Who we are

Aarne Ranta
Aarne Ranta
CEO & founder

Responsible for grammar resources. Invented the GF programming language in 1998 when working at Xerox Research Centre in Grenoble. He has worked at Chalmers University of Technology since 1999 and is currently Professor of Computer Science at the University of Gothenburg. He co-ordinated the European MOLTO project (Multilingual On-Line Translation) in 2010-2013, when many of the ideas now put into use in Digital Grammars were born.

Markus Forsberg
Markus Forsberg

Associate Professor of natural language processing and Director of Språkbanken (the Swedish Language Bank) at University of Gothenburg. His research is focused on language technology for Swedish throughout the ages and LT-based research infrastructures. He got a PhD in Computer Science at Chalmers University of Technology in 2007.

Krasimir Angelov
Krasimir Angelov

Responsible for the translation architecture and mobile applications. He is Associate Professor at the Department of Computer Science and Engineering at the University of Gothenburg. He has invented the algorithm for statistical parsing in GF and has made GF work on the large scale. He also has many years of industrial experience from SmartPro Ltd, Ontotext AD and Microsoft Research. He joined Chalmers University of Technology in 2008 and got a PhD there in 2012.

John J. Camilleri
John J. Camilleri
Chief developer

Our resident full-stack developer, with expertise ranging from formal methods and language technology to web development, mobile apps, UI and server admin. He has been active in the GF community for many years, creating both linguistic resources as well as developer tools. Joined the company in 2017 after completing his PhD in Computer Science at the University of Gothenburg.

Inari Listenmaa
Inari Listenmaa
Senior developer

Specialises in creating and testing language resources. An active contributor in the GF community since 2010, she has written and improved several resource grammars, and created a tool for automated test case generation for GF grammars. She finished her PhD in Computer Science at the University of Gothenburg in 2019.

Nima Ahmadyan
Nima Ahmadyan
Business developer

An entrepreneurial engineer who specialises in Business Development and Sales. He finished his studies in 2018, with an M.Sc. in Entrepreneurship and Business Design at Chalmers School of Entrepreneurship and a B.Sc. in Automation and Mechatronics at Chalmers University of Technology.

Work at Digital Grammars

We are always on the lookout for talented people to work with, both as consultants and as employees. If you are interested in working with us, you are very welcome to send us your CV and tell us what you think you can contribute to our company.


Digital Grammars is backed up by a world-wide community of open-source developers, who are hired as consultants when native speaker knowledge is needed of the customer's languages. This community is an efficient network, which enables us to find the consultants we need as a matter of days.

Digital Grammars also wants to give something back to the community. In addition to creating job opportunities, we sponsor research events and open source language software.

GF logo
Grammatical Framework

Digital Grammars is a contributor to the open-source GF project.

GF Summer School logo
Sixth GF Summer School 2018

Stellenbosch, South Africa


iLingual Tech logo
iLingual Tech

Shanghai, China