Att omvandla text till tal, och tvärtom. Det är vad KTH-forskaren Jens Edlund med kollegor fått drygt 20 miljoner kronor i anslag för att jobba med.
CLARIN (Common Language Resources and Technology Infrastructure) is an ESFRI initiative which aims at making language-based material available as primary research data to the humanities and social sciences (HSS) research communities with the help of the sophisticated language and speech processing tools and language resources (LRs) that have been developed over many years through research in language technology (LT), and taking advantage of the fact that increasing amounts of text and speech material – including historical material – are available in digital form, thus allowing for the utilization of unprecedented volumes of text and speech data in HSS research. The expectation is that this LT-based e-HSS paradigm will lead to completely new kinds of research as well as to new ways of addressing old research questions.
Digital humanities at Nodalida 2017
Nodalida conference took place in Gothenburg, Sweden, on 22-24 May 2017. It is a language technology conference aimed at Nordic and Baltic countries, but in fact attended by people from all continents. This year Nodalida celebrated its 40th anniversary.
Rada Michalcea (University of Michigan, USA) gave an invited talk "Computational Sociolinguistics", clearly relevant to the Clarin areas of interest.
Computational linguistics has come a long way, with many exciting achievements along several research directions, ranging from morphology and syntax to semantics and pragmatics. Simultaneously, there has been a tremendous growth in the amount of social media data available on web sites such as Blogger, Twitter, or Facebook, with all of these data streams being rich in explicit demographic information, such as the age, gender, industry, or location of the writer, as well as implicit personal dimensions such as personality and values. In this talk, I will describe recent research work undertaken in the Language and Information Technologies group at the University of Michigan, under the broad umbrella of computational sociolinguistics, where language processing is used to gain new insights into people’s values, behaviors, and world views. I will share the lessons learned along the way, and take a look into the future of this new exciting research area.
Watch Rada's talk: http://nodalida2017.se/mihalcea
Two European Research Council Advanced Grants - to Swe-CLARIN's steering group!
We congratulate David Strömberg, Stockholms Universitet, and Eva Hemmungs Wirtén, Linköping Universitet, on receiving an ERC Advanced Grant!
Recent NCN workshop
Venue: University of Gothenburg, Sweden, 3–4 May 2017
We had 30+ participants in the recent workshop organized by the Nordic CLARIN Network. The theme was Interaction design in the context of CLARIN. More information, and slides from presentations, can be found here.
Swe-CLARIN tools, research and publications
Swe-CLARIN focuses on development of tools and resources that can be used for research in digital humanities.
Links reflecting both research aimed at development of Swe-CLARIN infrastructure, and research made possible through use of Swe-CLARIN infrastructure is accessible here: https://sweclarin.se/eng/sweclarin_research