Closed theTechie closed 7 years ago
To this and similar questions: it's impossible for me to tell whether the difference is due to different computing environments or difference in implementation. Please try your best to confirm your implementation based on the tests and examples provided in class.
Sounds good. I have tried multiple examples manually computing probabilities inline with my implementation. All values sum up right.
All tests pass too.
Hi,
My final path probability is off by a large difference ~ 7.3e-10
Is this acceptable considering the variations based on different environments OR am i certainly wrong somewhere ?
model has 34 states ['$', "''", ',', '.', ':', 'CC', 'CD', 'DT', 'EX', 'IN', 'JJ', 'JJR', 'JJS', 'MD', 'NN', 'NNP', 'NNPS', 'NNS', 'POS', 'PRP', 'PRP$', 'RB', 'RBR', 'TO', 'VB', 'VBD', 'VBG', 'VBN', 'VBP', 'VBZ', 'WDT', 'WP', 'WRB', '``'] predicted parts of speech for the sentence ['Look', 'at', 'what', 'happened']
(['VB', 'IN', 'WP', 'VBD'], 9.301823359846707e-10)