@inProceedings{adesam-etal-2018-fsvreader-267311, title = {FSvReader – Exploring Old Swedish Cultural Heritage Texts}, abstract = {This paper describes FSvReader, a tool for easier access to Old Swedish (13th–16th century) texts. Through automatic fuzzy linking of words in a text to a dictionary describing the language of the time, the reader has direct access to dictionary pop-up definitions, in spite of the large amount of morphological and spelling variation. The linked dictionary entries can also be used for simple searches in the text, highlighting possible further instances of the same entry. }, booktitle = {CEUR Workshop Proceedings, vol. 2084. Proceedings of the Digital Humanities in the Nordic Countries 3rd Conference Helsinki, Finland, March 7-9, 2018. Edited by Eetu, Mäkelä Mikko, Tolonen Jouni Tuominen}, author = {Adesam, Yvonne and Ahlberg, Malin and Bouma, Gerlof}, year = {2018}, publisher = {University of Helsinki, Faculty of Arts}, address = {Helsinki}, } @inProceedings{adesam-etal-2018-eukalyptus-273839, title = {The Eukalyptus Treebank of Written Swedish}, booktitle = {Seventh Swedish Language Technology Conference (SLTC), Stockholm, 7–9 November 2018}, author = {Adesam, Yvonne and Bouma, Gerlof and Johansson, Richard and Borin, Lars and Forsberg, Markus}, year = {2018}, } @inProceedings{adesam-etal-2018-koala-273841, title = {The Koala Part-of-Speech and Morphological Tagset for Swedish}, booktitle = {Seventh Swedish Language Technology Conference (SLTC), Stockholm, 7-9 November, 2018}, author = {Adesam, Yvonne and Bouma, Gerlof and Johansson, Richard}, year = {2018}, } @article{eckhoff-etal-2018-proiel-265108, title = {The PROIEL treebank family: a standard for early attestations of Indo-European languages}, abstract = {This article describes a family of dependency treebanks of early attestations of Indo-European languages originating in the parallel treebank built by the members of the project pragmatic resources in old Indo-European languages. The treebanks all share a set of open-source software tools, including a web annotation interface, and a set of annotation schemes and guidelines developed especially for the project languages. The treebanks use an enriched dependency grammar scheme complemented by detailed morphological tags, which have proved sufficient to give detailed descriptions of these richly inflected languages, and which have been easy to adapt to new languages. We describe the tools and annotation schemes and discuss some challenges posed by the various languages that have been annotated. We also discuss problems with tokenisation, sentence division and lemmatisation, commonly encountered in ancient and mediaeval texts, and challenges associated with low levels of standardisation and ongoing morphological and syntactic change.}, journal = {Language Resources and Evaluation}, author = {Eckhoff, H. and Bech, K. and Bouma, Gerlof and Eide, K. and Haug, D. and Haugen, O. E. and Johndal, M.}, year = {2018}, volume = {52}, number = {1}, pages = {29--65}, }