Stagger – The Stockholm Tagger
   Stagger is a Swedish part-of-speech tagger based on Collins (2002) averaged perceptron. Per-token accuracy is about 96.6 percent (10-fold cross validation on SUC 3.0), which compares favorably to other published results for Swedish.

Spacos – Stockholm Parallel Corpus System
   Spacos is a system for finding word alignments in parallel corpora.

  efmaral is a tool for performing word alignment using Gibbs sampling with a Bayesian extension of the IBM alignment models.

Automated Essay Scoring
   We have developed a system for automatic grading of Swedish student essays (the national exam in Swedish B). On this page you can find the system source code, data and articles describing the project.

Stockholm Language Model with Entropy (SLME)
  SLME is a simple N-gram language model, inspired in spirit by the Stupid Backoff Model (Brants et al., 2007) but also designed to provide very fast calculation of the entropy of the distribution of words following a given context: E(p(word|context)).

Svek – Stockholms Vektormodeller
   This is a package for handling several different models that represent words using real-valued vectors: improved Collobert & Weston (2008, 2011) embeddings and (Reflective) Random Indexing (Cohen et al., 2010).

Swedish Python Routines (SPyRo)
   Swedish Python Routines (SPyRo) is a Python library for Swedish natural language processing.

Dialect maps
   A small tool for investigating regional differences in Swedish using data from bloggers from different parts of Sweden.

Stockholm TreeAligner
   Stockholm TreeAligner - A tool for aligning and searching parallel treebanks. The Stockholm TreeAligner allows you to create alignment links between corresponding nodes (or words) in two treebanks in different languages.


Section head: Robert Östling

Website URL:

Section for Computational Linguistics: