Differences
This shows you the differences between two versions of the page.
Next revision | Previous revision Next revision Both sides next revision | ||
courses:rg:2014:perceptron [2014/10/13 22:43] ufal created |
courses:rg:2014:perceptron [2014/10/13 22:56] ufal |
||
---|---|---|---|
Line 6: | Line 6: | ||
During the training, this best tag sequence for this sentence is found: | During the training, this best tag sequence for this sentence is found: | ||
N N X N X | N N X N X | ||
- | How would this result alter values of alpha_X,X,X, alpha_N,father? | + | How would this result alter values of // |
Supposing that the best tag sequence won't change, what would be your answer if " | Supposing that the best tag sequence won't change, what would be your answer if " | ||
2. Suppose this tagged sentence as the only entry in your training data: | 2. Suppose this tagged sentence as the only entry in your training data: | ||
a/DT boy/NN saw/VBD a/DT girl/NN with/IN a/DT nice/JJ hat/NN | a/DT boy/NN saw/VBD a/DT girl/NN with/IN a/DT nice/JJ hat/NN | ||
- | | + | How many features will a tagger from section 2.4 have, when its training is identical to the one from section 2.1? |
(For some reasons, you want to use all 36 tags from Penn Treebank tagset.) | (For some reasons, you want to use all 36 tags from Penn Treebank tagset.) | ||
- | Which tag sequence ('' | + | Which tag sequence (z< |
3. What is the difference between Maximum-Entropy and the Perceptron model training in the experiments? | 3. What is the difference between Maximum-Entropy and the Perceptron model training in the experiments? |