Please enable JavaScript.
Coggle requires JavaScript to display documents.
N-Gram Language (Independence Assumption
(Markov Assumption) (Predict…
N-Gram Language
-
-
-
-
Relative
Frequency
-
Example, word “Chinese” occurs 400 times
in a one million words corpus
MLE probability = 400/1000000
Evaluation
Instrinsic Evaluation
- Evaluate the quality of model independently
- Training & Test set
Extrinsic Evaluation
- Measure how much the application improves
-
Generalization & Zeros
-
If the probability of any word in the test set is 0,
the entire probability of the test set is 0
-