Tons of ressources for procedural text generation

Dictionnaire d'associations de noms libres

ConceptNet is a semantic network containing lots of things computers should know about the world, especially when understanding text written by people.

ConceptNet contains everyday basic knowledge:
learn - <MotivatedByGoal> - knowledge
You would learn because you want knowledge.

pos tagger with french support

softs & data for nlp on french

MElt is a freely available (LGPL) state-of-the-art sequence labeller that is meant to be trained on both an annotated corpus and an external lexicon.
MElt has been trained on various annotated corpus, using Alexina lexicons as source of lexical information. As a result, models for French, English, Spanish and Italian are included in the MElt package.

A programming language for multilingual grammar applications

Poetry generator

The Flickr API and Internet Archive Commons account to grab 18th century images based on specific themes like "biology" and "alchemy."
Processes the resulting illustrations to match background colors and discard undesirable images.
Uses a randomized corpus of the original Voynich Manuscript (from the EVA transcription) remapped to a public domain Voynich-like font.
Generates a set of themed "folios" based on the themes from the original manuscript.
Converts the output using CSS3 paged media to print-ready PDF (requires a local installation of Prince XML).