Allison Parrishthis is a little weird and worked a little better than I expected it to: using scikit-learn to fit gaussian mixtures to the vectors for all words following n-grams in the text, then doing nearest-neighbor lookups on the concatenated vectors for the n-grams, nearest-neighbor lookup on a sample from the mixture model, and chaining predictions like a markov chain
Jonkman Microblog is a social network, courtesy of SOBAC Microcomputer Services. It runs on GNU social, version 1.2.0-beta5, available under the GNU Affero General Public License.
All Jonkman Microblog content and data are available under the Creative Commons Attribution 3.0 license.