@inProceedings{Tahmasebi-Nina2016-233899, title = {SWE-CLARIN – the Swedish CLARIN project – aims and activities}, booktitle = {Digital Humanities in the Nordic countries, Oslo, March 15-17 2016}, author = {Tahmasebi, Nina and Borin, Lars and Jordan, Caspar and Ekman, Stefan}, year = {2016}, pages = {122--123}, } @inProceedings{Nusko-Bianka2016-238135, title = {Building a Sentiment Lexicon for Swedish}, abstract = {In this paper we will present our ongoing project to build and evaluate a sentiment lexicon for Swedish. Our main resource is SALDO, a lexical resource of modern Swedish developed at Språkbanken, University of Gothenburg. Using a semi-supervised approach, we expand a manually chosen set of six core words using parent-child relations based on the semantic network structure of SALDO. At its current stage the lexicon consists of 175 seeds, 633 children, and 1319 grandchildren.}, booktitle = {Linköping Electronic Conference Proceedings}, author = {Nusko, Bianka and Tahmasebi, Nina and Mogren, Olof}, year = {2016}, volume = {126}, number = {006}, ISBN = {978-91-7685-733-5}, pages = {32----37}, } @misc{Eide-StianRødven2016-238134, title = "The Swedish Culturomics Gigaword Corpus: A One Billion Word Swedish Reference Dataset for NLP", author = "Eide, Stian Rødven and Tahmasebi, Nina and Borin, Lars", year = "2016", volume = "126", number = "002", isbn = "978-91-7685-733-5 ", pages = "8--12", } @inProceedings{Eide-StianRødven2016-250073, title = {The Swedish Culturomics Gigaword Corpus: A One Billion Word Swedish Reference Dataset for NLP}, abstract = {In this paper we present a dataset of contemporary Swedish containing one billion words. The dataset consists of a wide range of sources, all annotated using a state-of-the-art corpus annotation pipeline, and is intended to be a static and clearly versioned dataset. This will facilitate reproducibility of experiments across institutions and make it easier to compare NLP algorithms on contemporary Swedish. The dataset contains sentences from 1950 to 2015 and has been carefully designed to feature a good mix of genres balanced over each included decade. The sources include literary, journalistic, academic and legal texts, as well as blogs and web forum entries.}, booktitle = {Linköping Electronic Conference Proceedings. Digital Humanities 2016. From Digitization to Knowledge 2016: Resources and Methods for Semantic Processing of Digital Works/Texts, July 11, 2016, Krakow, Poland}, author = {Eide, Stian Rødven and Tahmasebi, Nina and Borin, Lars}, year = {2016}, publisher = {Linköping University Electronic Press}, adress = {Linköping}, ISBN = {978-91-7685-733-5}, }