Natural Language Processing Nptel Week 7 Quiz Answers

Are you looking for Natural Language Processing Nptel Week 7 Quiz Answers? You’ve come to the right place! Access the most accurate answers at Progiez.

---

Natural Language Processing Nptel Week 7 Quiz Answers (Jan-Apr 2025)

Course Link: Click Here

---

Que. 1
Suppose you have a raw text corpus and you compute a word co-occurrence matrix from there. Which of the following algorithm(s) can you utilize to learn word representations? (Choose all that apply)

a) CBOW
b) SVD
c) PCA
d) GloVe

View Answer

---

Que. 2
What is the method for solving word analogy questions like, given A, B, and D, find C such that A:B::C:D, using word vectors?

a) Vc=Va+(Vb−Va)V_c = V_a + (V_b – V_a), then use cosine similarity to find the closest word of VcV_c.
b) Vc=Va+(Vd−Vb)V_c = V_a + (V_d – V_b), then do dictionary lookup for VcV_c.
c) Vc=Va+(Va−Vp)V_c = V_a + (V_a – V_p), then use cosine similarity to find the closest word of VcV_c.
d) Vc=Va+(Va−Vb)V_c = V_a + (V_a – V_b), then do dictionary lookup for VcV_c.
e) None of the above

View Answer

---

Que. 3
What is the value of PMI(w1,w2)PMI(w_1, w_2) for C(w1)=100C(w_1) = 100, C(w2)=2500C(w_2) = 2500, C(w1,w2)=320C(w_1, w_2) = 320, N=50000N = 50000?

NN: Total number of documents.
C(w1)C(w_1): Number of documents where w1w_1 has appeared.
C(w1,w2)C(w_1, w_2): Number of documents where both words have appeared.

Note: Use base 2 in logarithm.

a) 4
b) 5
c) 6
d) 5.64

View Answer

---

Que. 4
Given two binary word vectors w1w_1 and w2w_2 as follows:

w1=[1010011010]w_1 = [1010011010]
w2=[0011111100]w_2 = [0011111100]

Compute the Dice and Jaccard similarity between them.

a) 6/11, 3/8
b) 10/11, 5/6
c) 4/9, 2/7
d) 5/9, 5/8

View Answer

---

Que. 5
Consider two probability distributions for two words pp and qq. Compute their similarity scores with KL-divergence.

p=[0.20,0.75,0.50]p = [0.20, 0.75, 0.50]
q=[0.90,0.10,0.25]q = [0.90, 0.10, 0.25]

Note: Use base 2 in logarithm.

a) 4.704, 1.720
b) 1.692, 0.553
c) 2.246, 1.412
d) 3.213, 2.426

View Answer

---

Que. 6
Consider the following word co-occurrence matrix given below. Compute the cosine similarity between:

(i) w1w_1 and w2w_2, and
(ii) w1w_1 and w3w_3.

	w4w_4	w5w_5	w6w_6
w1w_1	2	8	5
w2w_2	4	9	7
w3w_3	1	2	3

a) 0.773, 0.412
b) 0.881, 0.764
c) 0.987, 0.914
d) 0.897, 0.315

View Answer

---

Que. 7

‘Which ofthe folowing types of relations can be captured by word2vec (CBOW or
Skipgram)?

1. Analogy (A:B::C:?)
2. Antonymy
3. Polysemy
4. All of the above

View Answer

---

Natural Language Processing Nptel Week 7 Quiz Answers

For answers to others Nptel courses, please refer to this link: NPTEL Assignment