@inProceedings{Johansson-Richard2016-233140, title = {A Multi-domain Corpus of Swedish Word Sense Annotation}, abstract = {We describe the word sense annotation layer in Eukalyptus, a freely available five-domain corpus of contemporary Swedish with several annotation layers. The annotation uses the SALDO lexicon to define the sense inventory, and allows word sense annotation of compound segments and multiword units. We give an overview of the new annotation tool developed for this project, and finally present an analysis of the inter-annotator agreement between two annotators. }, booktitle = {10th edition of the Language Resources and Evaluation Conference, 23-28 May 2016, Portorož (Slovenia)}, author = {Johansson, Richard and Adesam, Yvonne and Bouma, Gerlof and Hedberg, Karin}, year = {2016}, publisher = {European Language Resources Association}, ISBN = {978-2-9517408-9-1}, } @techreport{Borin-Lars2016-233768, title = {A free cloud service for OCR / En fri molntjänst för OCR}, author = {Borin, Lars and Bouma, Gerlof and Dannélls, Dana}, year = {2016}, publisher = {University of Gothenburg}, adress = {Göteborg}, } @article{Adesam-Yvonne2016-237884, title = {Språkteknologi för svenska språket genom tiderna}, abstract = {Språkbanken, the Swedish Language Bank, is a language technology research unit at the Department of Swedish, University of Gothenburg. We develop language resources – such as corpora, lexical resources, and analytical tools – for all variants of Swedish, from Old Swedish laws to present-day social media. Historical texts offer exciting theoretical and methodological challenges for language technology because they often defy the assumption inherent in most automatic analysis tools that the texts contain a standardized written language. In this article, we describe our ongoing work on the development of annotated historical corpora, as well as our efforts on linking various resources (both corpora and lexical resources). This research advances the state of the art of language technology as well as enables new research for scholars in other disciplines.}, author = {Adesam, Yvonne and Ahlberg, Malin and Andersson, Peter and Borin, Lars and Bouma, Gerlof and Forsberg, Markus}, year = {2016}, volume = {76}, number = {Studier i svensk språkhistoria 13}, pages = {65--87}, } @inProceedings{Adesam-Yvonne2016-251827, title = {Old Swedish Part-of-Speech Tagging between Variation and External Knowledge}, booktitle = {Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities, Berlin, Germany, August 11, 2016}, author = {Adesam, Yvonne and Bouma, Gerlof}, year = {2016}, publisher = {Association for Computational Linguistics}, adress = {Stroudsburg, PA }, ISBN = {978-1-945626-09-8}, } @inProceedings{Bouma-Gerlof2016-251825, title = {Multiword Annotation in the Eukalyptus Treebank of Written Swedish}, booktitle = {PARSEME, 6th general meeting, 7-8 April 2016, Struga, FYR Macedonia }, author = {Bouma, Gerlof and Adesam, Yvonne}, year = {2016}, } @inProceedings{Bouma-Gerlof2016-254389, title = {Part-of-speech and Morphology Tagging Old Swedish}, booktitle = {Proceedings of the Sixth Swedish Language Technology Conference (SLTC) Umeå University, 17-18 November, 2016}, author = {Bouma, Gerlof and Adesam, Yvonne}, year = {2016}, } @inProceedings{Cap-Fabienne2016-254388, title = {SWORD: Towards Cutting-Edge Swedish Word Processing}, abstract = {Despite many years of research on Swedish language technology, there is still no well-documented standard for Swedish word processing covering the whole spectrum from low-level tokenization to morphological analysis and disambiguation. SWORD is a new initiative within the SWE-CLARIN consortium aiming to develop documented standards for Swedish word processing. In this paper, we report on a pilot study of Swedish tokenization, where we compare the output of six different tokenizers on four different text types. For one text type (Wikipedia articles), we also compare to the tokenization produced by six manual annotators.}, booktitle = {Proceedings of the Sixth Swedish Language Technology Conference (SLTC) Umeå University, 17-18 November, 2016}, author = {Cap, Fabienne and Adesam, Yvonne and Ahrenberg, Lars and Borin, Lars and Bouma, Gerlof and Forsberg, Markus and Kann, Viggo and Östling, Robert and Smith, Aaron and Wirén, Mats and Nivre, Joakim}, year = {2016}, }