Explore @kuhumcst Open Source projects

Centre for Language Technology, University of Copenhagen (@kuhumcst)

kuhumcst

Stars
191
Global Org. Rank 41,410 (Top 14 %)
Registered almost 13 years ago
Most used languages

Clojure
47.4 %

C++
21.1 %

Java
10.5 %

PHP
5.3 %

C
5.3 %

Jupyter Notebook
5.3 %

Roff 5.3 %
Location 🇩🇰 Denmark
Country Total Rank 550
Country Ranking

Clojure
8

Roff 8

C++
78

Java
256

PHP
293

C
404

Jupyter Notebook
526

cstlemma

Lemmatiser for Danish, Dutch, English, German, Polish, Romanian, Russian and tens of other languages, that uses affix rules (affix: prefix, infix, suffix, circumfix). Rules are obtained by supervised learning from a full form - lemma list.

stucco

An experimental adaptive UI toolkit.

xml-hiccup

Convert XML into Hiccup in Clojure and ClojureScript.

DanNet

The Danish WordNet as an RDF graph.

taggerXML

Modernized version of Eric Brill's Part Of Speech tagger.

tf-idf

A reasonably performant TF-IDF implementation.

Danish-Similarity-Dataset

Gold standard resource for evaluation of Danish word embedding models.

rescope

Turn documents into UI components.

pedestal-sp

Turn a Pedestal web service into a SAML Service Provider.

rtfreader

Text segmenter and tokeniser for Danish, English and other languages. Reads an RTF or flat text file and outputs the text, one line per sentence & optionally tokenized.

texton

Text Tonsorium - a toolbox that automatically arranges NLP tools in workflows and enacts them with user's inputs

Anvil-Facetracker

OpenCV-based Plugin for the Anvil annotation software that tracks faces and creates annotations when velocity or acceleration thresholds are transgressed.

danish-semantic-reasoning-benchmark

A Danish semantic reasoning benchmark compiled from lexical semantic resources

cuphic

Transform or scrape Hiccup with a declarative DSL.

glossematics

The life of Louis Hjelmslev.

affixtrain

Using supervised learning, create a set of affix rules for use by the CSTlemma lemmatiser.

letterfunc

Functions for upper/lower casing, for testing whether a character is a letter and for conversion between Unicode encodings UTF-8 and UTF-16

texton-Java

Web-based workflow management system that computes candidate tool workflows given input file(s) and the user's requirements regarding the output. Afterwards, runs a workflow selected by the user from the list of candidates. Implemented in Bracmat (~75%) and Java (~25%).

qname

A QName record and conversions between QNames, Keywords, and IRI strings.

texton-linguistic-resources

Linguistic resources for several of the tools included in the Text Tonsorium

head_movement_detection

Jupyter notebooks and training data containing manual head movement annotations, speech data and velocity, acceleration and jerk data.

Jupyter Notebook