The morphological annotation in the Swedish UD treebanks follows the general guidelines and does not add any language-specific features. The following may be noted:
- XPOSTAG: There are two sets of language-specific tags in use for Swedish. UD Swedish adopts the tagset of the Stockholm-Umeå Corpus, while UD Swedish-LinES uses a different inventory based on Tapanainen and Järvinen (1997).
- FEATS: Features are currently lacking in UD Swedish-LinES.
- LEMMA: Lemmas in UD Swedish are based on SALDO (Borin et al., 2008). Lemmas are currently lacking in UD Swedish-LinES.
Lars Borin, Markus Forsberg, Lennart Lönngren. 2008. Saldo 1.0 (Svenskt associationslexikon version 2). Språkbanken, Göteborg universitet
Pasi Tapanainen and Timo Järvinen. 1997. A Non-projective Dependency Parser. In Proceedings of the Fifth Conference on Applied Natural Language Processing, 64-71.
The Stockholm Umeå Corpus. Version 2.0. 2006. Stockholm University: Department of Linguistics.