Språkbanken Text

We are a research unit and also form part of Nationella språkbanken (the National Language Bank) a national e-infrastructure supporting research based on language data. Språkbanken was established in 1975 in recognition of the groundbreaking corpus linguistic work initiated by Sture Allén. Our work focuses on language technology, in particular methodologies for handling the Swedish language, and the development of linguistic resources and tools for Swedish. These language resources are made available to researchers in language technology and other disciplines, as well as to the general public.
Read more...

Språkbanken FAQ with common questions and answers (in Swedish).

Språkbanken on GitHub

Follow the development of our projects and download our source code

Språkbanken's API documentation

Documentation for our web services

New words in SALDO

2019-09-02 10:11:
Förenta_staterna Staterna abugida avkraga avkragad avkragande avkragande² avkragning be_att_få_återkomma dugga_tätt fest_i_Kapernaum glajor gudars_skymning heläga helägande helägande² hålla_flabben hålla_truten hålla_vatten klinga_falskt

2019-04-08 08:56:
georadar grå_celler gå_på_grund hämta_upp jordradar köpa_på_sig markradar stöta_på_grund troakar vild² vild³

2019-03-22 19:06:
tvångsmedicinera tvångsmedicinerad tvångsmedicinerande tvångsmedicinerande² tvångsmedicinerbar tvångsmedicinerbarhet tvångsmedicinering

Research

DReaM

Computational tools for accessing the world’s linguistic heritage.

ALZ-RJ

Linguistic and extra-linguistic parameters for early detection of cognitive impairment.

Diabase
Language technology for historical resources – towards diachronic text analysis.

Culturomics

Towards a knowledge-based culturomics, information extraction from Swedish text, focusing on sentiment analysis tools, and automatic language change detection.