The mission of Digital Grammars is to develop reliable solutions for the multilingual market. We offer:
Our solutions are available both as stand-alone programs, web APIs, and mobile apps with text and speech input and output.
25-27 July 2016: Digital Grammars sponsors
in Aberdeen, Scotland.
31 May 2016: Digital Grammars presentation at EAMT-2016 in Riga, Latvia.
26 May 2016: Grammatical Framework presentation at foss-north in Gothenburg, Sweden.
Digital Grammars provides translation solutions for producers of information. They are tailored for the needs of the customer and deliver translations whose quality is good enough for publication. This is in contrast to the usual translation systems on the web, which are made for consumers rather than producers. Such systems are meant to translate just anything, but the results are not reliable. You cannot use them to publish your content.
Our translation solutions are custome-made to follow your terminology and style guidelines. You can safely use them to publish your content, with no or just a little manual corrections (post-editing). Our translation tools assess the confidence of translations, so that post-editors can focus on those parts that might need attention.
Digital Grammars translation solutions are highly multilingual, with a potential for over 30 languages. The more languages you need, the more cost-efficient it is to use our solutions.
Our translation is based on meaning: we analyse the content of the source text and render the same meaning in the target language.
Data-Driven Documentation is applicable if your content already exists as machine-readable data: for instance, databases, product catalogues, financial reports and sports results.
The technology also supports text robots, which produce text in real time from streamed data - of course in many parallel languages if you want.
Data-Driven Translation can be smoothly combined with translation, if your content is a mixture of free text and data.
The meaning analysis used in Data-Driven Documentation also makes it possible to process queries. The queries can be very accurate and complex, similarly SQL queries in a database. This is much more powerful than usual string-based search.
Digital Grammars search and question answering is of course multilingual: your customers can make the queries in their own languages, and they will get answers in the same language. But the answers can be found in a set of sources written in other languages.
All of our produces can be delivered in different formats:
TD (Tillgänglighetsdatabase, Accessibility Database), is a web service that gives information related to accessibility to buildings and services. TD is a unit of the Västra Götaland regional government in Sweden.
Digital Grammars has built a second generation of translations for TD, addressing Finnish, German, and Spanish. These translations are used in the TD web page, which however also has translations coming from other sources (mainly manual).
Talkamatic is a company addressing voice communication in mobile, web, and automotive applications.
Digital Grammars has made the Talkamatic Dialogue Management multilingual by extending it from English and Swedish to Chinese, Dutch, French, German, Italian, and Spanish.
DART is a team of assistive technology experts under the Department of Neurology, Psychiatry and Habilitation of Sahlgrenska University Hospital, Gothenburg, Sweden.
Digital Grammars works for DART within the InLife project (INdependent LIving support Functions for the Elderly). Starting from a list of 2000 words and phrases, we have developed a translator and natural language generator for English, Finnish, German, Slovene, and Swedish.
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.
Grammar Engineering for a Customer: a Case Study with Five Languages. By A Ranta, C Unger, DV Hussey - ACL/GEAF 2015, 2015. pdf
Embedded Controlled Languages. By A Ranta - Controlled Natural Language, LNCS/LNAI 2014. pdf
Speech-enabled hybrid multilingual translation for mobile devices. By K Angelov, B Bringert, A Ranta - EACL 2014, 2014. pdf
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. He is Associate Professor of natural language processing and Co-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. 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 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.
Surface mail: Digital Grammars AB, Framnäsgatan 23, 41264 Göteborg, Sweden.
Digital Grammars Gothenburg AB, org.nr. 556964-3249