There would be need to a state specifically for “the cow jumped over the” (and any other relevant context) and states for all the other times ‘the’ is proceeded by something.
This is the limitation i was getting at btw. In the example i wad getting at, if you have an image with solid vertical columns, followed by columns of random static, followed again by solid vertical colors a markov chain could eventually learn all patterns that go
solid->32 random bits->different solid color
And eventually it would start predicting the different color correctly based on the solid color before the randomness. It ‘just’ needs a state for every possible random color between. This is ridiculous in practice however since you’d need to learn 2^32 states just for relation ship between those two solid colors alone.
The pure n-gram language models would have hard time computing escape weights for such contexts, but mixture of probabilities that is used in SNMLM does not need to do that.
If I may, I've implemented an online per-byte version of SNMLM [2], which allows skipgrams' use. They make performance worse, but they can be used. SNMLM's predictive performance for my implementation is within percents to performance of LSTM on enwik8.
This is the limitation i was getting at btw. In the example i wad getting at, if you have an image with solid vertical columns, followed by columns of random static, followed again by solid vertical colors a markov chain could eventually learn all patterns that go
solid->32 random bits->different solid color
And eventually it would start predicting the different color correctly based on the solid color before the randomness. It ‘just’ needs a state for every possible random color between. This is ridiculous in practice however since you’d need to learn 2^32 states just for relation ship between those two solid colors alone.