provides language technology for content producers. We offer
Digital Grammars Gothenburg AB, org.nr. 556964-3249
Aarne Ranta, CEO, is also responsible for grammar resources. He invented the GF programming language in 1998 when working at Xerox Research Centre in Grenoble. He has worked at Chalmers since 1999 and is currently Professor of Computer Science at the University of Gothenburg. He coordinated 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. More...
Markus Forsberg, Board Chairman, is also responsible for lexical resources. He is the CTO of Språkbanken (the Swedish Language Bank) and one of the main architects of its rich language resources since 2008. His research is focused on language technology for Swedish throughout the ages. He got a PhD in Computer Science at Chalmers University of Technology in 2007. More...
Thomas Hallgren, Vice President, is also responsible for the GF compiler, web applications, and user interfaces. He is Research Engineer at the Department of Computer Science and Engineering at the University of Gothenburg and has a long experience in functional programming, compilers, and advanced graphical user interfaces. He got a PhD in Computer Science at Chalmers University of Technology in 1998. More...
Krasimir Angelov, CTO, is also responsible for the translation architecture and mobile applications. He is Assistant 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. More...
Digital Grammars builds on the Grammatical Framework, GF, which is a software system for multilingual translation and other applications of grammars. GF works in the same way as compilers, which translate program code into machine code. The translation is based on an abstract semantic representation, which guarantees that the source and the target have the same meaning. This model for processing is perfect for the main mission of Digital Grammars - to create language technology that one can rely on.
The key to reliability is the development of technologies that can be understood and where problems can be traced back to their origins. The proliferation of statistical methods in language technology led to a situation where the outcome of a process is hard to predict and almost impossible to control. In exchange, statistical methods give us robust systems with wide coverage but at the cost that certain error rate must be tolerated. In Digital Grammars we bet on carefully designed and verified language resources which give us high precision. Since we focus on producer oriented translation, we sometimes sacrifice coverage for precision. We still welcome statistical methods for rapid bootstrapping of new resources or in situations where we have to deal with incomplete information.
GF has been applied to over 30 languages and has large resources for processing them. The GF community has over 100 active members around the world. In addition to this, Digital Grammars has expert knowledge about the rich language resources of Språkbanken, the Swedish Language Bank, which is a leading producer of resources for Swedish. The cooperation between GF and Språkbanken has long traditions within the Centre for Language Technology at the University of Gothenburg.
Both GF and most resources of Språkbanken are available as open-source software. They have liberal licenses (BSD and LGPL for GF, Creative Commons for Språkbanken) which allow anyone to build anything on top of them. This liberality includes proprietary applications: the customers’ data, as well as whatever we build on top of the underlying resources for the customer, can be kept confidential and proprietary if wanted.
At the same time, we continue supporting the development of open-source software. Improvements in the basic grammar libraries will benefit all proprietary applications built on top of them, for free. And the digital access to the grammars of the languages of the world will benefit everyone!
Digital Grammars provides services that adapt its technology to the customer’s needs. We invite you to contact us via firstname.lastname@example.org and discuss your needs for language technology solutions. Two good indications for projects where we can help you are
This is in contrast to most of the well known multilingual software, where the objective is rough translation. They give an idea what a document is about, but no guarantees that the meaning is preserved. Our mission is to enable translations that you can be confident to publish. If you change the content of the source document, the changes can be automatically propagated to all translations.
Here is a sample of functionalities from which we have previous experience. The applications can be built on different platforms
Translation is a core application of Digital Grammars, targeting high-quality tasks with possibly a high number of simultaneous languages. We can tailor systems that enable you to keep create multilingual content and keep it in synchrony. We support both fully automatic translation and interactive workflows that involve human judgement and post-editing.
Question answering in natural language is often the best way to get access to rich data. We can help build systems that work seamlessly with your content translator, and also systems that work independently of translation.
Localization grammars is the logical next step from localization databases - a transition from pasting static text to generating text dynamically. We can make sure that your messages are rendered correctly in new situations and new languages.
Advanced business reports can combine diagrams with text which is automatically generated on the basis of your business data. Similarly software systems can generate automatic messages triggered by the presence of new data. By using grammars we can ensure that the generated text is always coherent and flawless.
Multilingual websites are an integrated application involving translation, information retrieval, and localization. Integrating all these components can save money and time, and give a coherent impression and user experience.
We can use the grammar resources in GF and Språkbanken, in combination with your own language resources, to build interactive tools for language teaching, both on the web and as mobile applications.
The following demos were produced in earlier projects using GF technology. These are research demos showing some of the potential and fully open-source. The products of Digital Grammars build on the same technology but adapt it to the needs of our customers.
Human Language Compiler (new, wide coverage, speech-enabled, experimental)
Phrasedroid (old, tourist phrasebook only)