|
|
|
|
|
by rincebrain
3689 days ago
|
|
I haven't looked at the source, but the linked page claims to use a Markov model trained on an English corpus (in this case, A Tale of Two Cities), so it emits English-like sequences of letters and spacing, and uses that in conjunction with a Huffman tree setup to map random bitstrings to the pseudo-English phrases. You could use this on $LANGUAGE of your choice, or $CORPUS of your choice. (Also, it seems much more memorable to me than an equivalent random stream of bits are.) |
|
Still, neither "wrowd", nor "aut", nor "settea" looks or sounds English-like to me. I wouldn't even begin to know how to pronounce it.
It's nice in a sense, sure, but I suppose I could even remember (real) French words better, despite all those accents and me not speaking French.