Wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

ML_Techniques_I Week 4 Session 1

Total questions: 5

Worksheet time: 3mins

Name
Class
Date
1.

Removing all stop-words from text always improves the performance of any downstream NLP model.

a)

True

b)

False

2.

In CBOW (Continuous Bag of Words), the model predicts a context word given the center word.

a)

True

b)

False

3.

In the Skip-Gram model, what is the primary training objective?

a)

Predict the center word given its surrounding context

b)

Predict surrounding context words given the center word

c)

Maximize TF-IDF scores of rare words

d)

Factorize the co-occurrence matrix

4.

TF-IDF down-weights terms that:

a)

Appear in many documents

b)

Appear rarely across the corpus

c)

Occur only in the test set

d)

Are longer than a threshold

5.

During an analogy test (“king” – “man” + “woman” ≈ “queen”), Word2Vec actually searches for

a)

Euclidean distance to the target vector

b)

Word frequency score

c)

Cosine similarity to the target vector

d)

Dot product with the centroid of all vector