2. C01] A. Write 4 distinct issues that you may face while performing English language tokenization. B. Fill in the blank: Paris is to France as Oslo is to a. Sweden, b. Denmark, c. Norway, d. Finland You may find necessary information and hints at the bottom of this page.

icon
Related questions
Question

correction: hint for 2b

Hint for 2C: This type of problem is called analogy, and it works like this: pick X that maximizes
cosine(C, A B + X) where A, B, C and X are all vectors. You may use these word vectors
(presented alphabetically):
Denmark = [0, 0, 1, 2], Finland= [1, 1, 1, 0], France = [3, 2, 1, 0], Norway = [3, 2, 3, 2],
Oslo = [1, 2, 1, 1], Paris = [3, 4, 0, 1], Sweden = [3, 1, 1, 1]
Transcribed Image Text:Hint for 2C: This type of problem is called analogy, and it works like this: pick X that maximizes cosine(C, A B + X) where A, B, C and X are all vectors. You may use these word vectors (presented alphabetically): Denmark = [0, 0, 1, 2], Finland= [1, 1, 1, 0], France = [3, 2, 1, 0], Norway = [3, 2, 3, 2], Oslo = [1, 2, 1, 1], Paris = [3, 4, 0, 1], Sweden = [3, 1, 1, 1]
2.
[CO1]
A. Write 4 distinct issues that you may face while performing English
language tokenization.
B. Fill in the blank: Paris is to France as Oslo is to
a. Sweden, b. Denmark, c. Norway, d. Finland
You may find necessary information and hints at the bottom of this page.
Transcribed Image Text:2. [CO1] A. Write 4 distinct issues that you may face while performing English language tokenization. B. Fill in the blank: Paris is to France as Oslo is to a. Sweden, b. Denmark, c. Norway, d. Finland You may find necessary information and hints at the bottom of this page.
Expert Solution
steps

Step by step

Solved in 4 steps

Blurred answer