Name: Språkbanken
Type: Organization
Bio: Språkbanken Text is a research unit and also forms part of Nationella språkbanken, a national e-infrastructure supporting research based on language data.
Location: Göteborg, Sweden
Blog: https://spraakbanken.gu.se/
Språkbanken's Projects
Models for the Sparv pipeline
Språkbanken's text analysis tool
Central registry for Sparv Pipeline plugins
REST-API for listing Sparv plugins and validating plugin manifests
Template for writing plugins for the Sparv Pipeline (https://github.com/spraakbanken/sparv-pipeline)
Extension for Sparv containing a wrapper for FreeLing
Sparv plugin for generating word frequency files for the Kubord 2 project
Sparv plugin for SBX specific export of metadata
Word-sense disambiguation tool based on SALDO
Metadata sources for all service providers in the CLARIN Service Provider Federation
Code for collecting SFS
elasticsearch plugin needed by strix
The frontend of Strix
A Swedish Natural Language Understanding Benchmark
Programme for crawling SVT's API for news articles and converting the data to XML.
Statistics for Swedish tweets over the period 2018-2022
Editor for normalising learner texts (error annotation and tagging.)
Guidelines, documentation, instructions, issues, etc.
Pseudonymizer for the SweLL-project
Pseudonymization web service using SamirYousuf's rule-based pseudonymizer
Documentation for the initial release of the SweLL infrastructure
Simple functions to manipulate text
Syntax tree visualiser
Script for collecting tweets using Twitter's streaming API
valens-extract
Small flask application for validation META-SHARE XML files.