← Back to context Comment by kragen 6 days ago You can just use 2-grams of Unicode code points. 1 comment kragen Reply npb 5 days ago Very much agree. Character bigrams will solve this perfectly with tiny amounts of training data (like a couple KB).
npb 5 days ago Very much agree. Character bigrams will solve this perfectly with tiny amounts of training data (like a couple KB).
Very much agree. Character bigrams will solve this perfectly with tiny amounts of training data (like a couple KB).