Awesome Swedish

A curated list of awesome resources for Swedish language processing.

To keep the list up to date, don't hesitate to make a pull request for new libraries and projects on the Swedish language.

NLP Libraries and models with Swedish support

• Fasttext pre-trained vectors
• Swedish Spacy: trained model by KB. Has NER support.
• Spacy: Supports the Swedish language. Basic language data (stop words, tag maps, morph rules, lemmatization) are, but no model is trained on them (still can be used for basic tasks).
• SweBERT: Arbetsförmedlingen's Swedish BERT models
• Bert Swedish among other 101 languages is available for download.
• Lemmy 🤘Lemmy is a lemmatizer for Danish 🇩🇰 and Swedish 🇸🇪
• Deplacy CUI-based Tree Visualizer for Universal Dependencies and Immediate Catena Analysis

Datasets

• stopwords-sv List of stop words for Swedish
• Swedish Treebank
• SpråkbankenText List of various corpus and lexicons in the Swedish language.
• Swedish Language Data Lab - A work in progress.
• Universal Dependencies With Swedish and Swedish Sign Language support.
• Swedish poetic corpus

Research papers and work

• En recommended svensk språkteknologisk terminologi
• Talbanken05: A Swedish Treebank with Phrase Structure and Dependency Annotation
• LinES: An English-Swedish Parallel Treebank
• Towards a Swedish Medical Treebank