'Tour de CLARIN: Sweden' blog post written by Darja Fišer and Jakob Lenardič
The Swedish consortium SWE-CLARIN, which has been a member of CLARIN ERIC since 2014, is a collaboration between the national archive Riksarkivet, the Swedish National Data Service, the Swedish language council Språkrådet, the KTH School of Computer Science and Communication and a variety of language technology research units at five universities – the Department of Computer and Information Science at Linköping University, the Humanities Lab at Lund University, Språkbanken (the Swedish Language Bank) at the University of Gothenburg, the Department of Linguistics at Stockholm University, and the Computational Linguistics Group at Uppsala University. The national coordinator of SWE-CLARIN is Lars Borin, professor of natural language processing at the University of Gothenburg and co-director of Språkbanken
The coordinating centre of SWE-CLARIN is Språkbanken (the Swedish Language Bank), a major national and international research centre on computational approaches to language in Sweden, established already in the 1970s, which provides researchers with access to language resources, including an extremely wide range of Swedish texts, as well as state-of-the-art computational tools for the processing, compilation and linguistic analysis of corpora. The rapidly-increasing number of corpora, which are in the majority of cases available for download in standard formats, not only comprise a comprehensive collection of contemporary Swedish texts representing a wide variety of formal and informal discourse produced both in Sweden and Finland, where Swedish is an official language, but also include historical texts from most periods of written Swedish.
Related to the corpora are the tools of Språkbanken, e.g., the corpus infrastructure Korp, used for accessing both the above mentioned corpora, the Finnish corpora made available by FIN-CLARIN in the Language Bank of Finland, the Saami corpora provided by the Norwegian CLARIN Giellatekno node in Tromsø, and Estonian corpora available through the Estonian CLARIN EKRK centre, or the annotation tool Sparv, presenting a web-based interface to the Korp annotation toolchain, offering part-of-speech tagging, compound analysis, word sense disambiguation, named entity recognition and dependency parsing of Swedish text. Additionally, Språkbanken researchers are working in a great number of research projects – one such endeavour is the research program Towards a knowledge-based culturomics, among whose goals is “to advance the state of the art in language technology resources and methods for semantic processing of Swedish text, in order to provide researchers and others with more sophisticated tools for working with the information contained in large volumes of digitized text, e.g., by being able to correlate and compare the content of texts and text passages on a large scale”.
SWE-CLARIN has also organized successful User Involvement events. One such event was the Second National Swe-Clarin workshop held in connection with the Swedish Language Technology Conference in November 2016, where two invited presentations were given, one on the text mining project BiographyNet and the other on the impact language technology has on scholarship in the humanities, followed by a poster session featuring Swedish CLARIN-supported research.
Click here to read more about Tour de CLARIN