Category: nlp
#Uncategorized #coffee #ngram
So I got my hands of the Google N-gram data for the Romanian language. It’s noisy as hell, has some other subtle issues too, but here’s the first thing I noticed:
The Romanian word for coffee is cafea, and the more you crave it, the longer you pronunce …
Category: nlp
#alternations #computational linguistics #infinitives #pca #principal components analysis #nlp #scikit-learn
One of the problems we tackled here at my university is one as old as the modern Romanian language. It is a problem for linguists, as well as for foreigners trying to learn the language. We call it the root alternations problem.
Similar to French and other languages, Romanian verbs …