Johannes Gontrum's repositories
PennToPCFG
Learns an unlexicalized PCFG from a Penn Treebank
moodcontrol
Code of our hackathon-winning proof-of-concept. (codeFEST8)
WikipediaImageCrawler
Recursively extracts images that are assigned to a category in Wikipedia.
TwitterScripts
Collection of Python scripts to extract data from a Tweet database
AStarParser
Basic implementation of the A* parsing algorithm introduced by Klein and Manning in 2003
datasharing
The Leek group guide to data sharing
histogramPostprocessor
Analyses data and lets you create histograms in LaTeX with a build-in console. Created for a class at university.
spellchecker
Context sensitive spell checker that can be trained on plain text. Project for an automaton class at university.
Tweets2SQL
Filter the Twitter Stream and store the Tweets in a MySQL database