Total No. of Questions : 8] SEAT No.

8
23
P6566 [Total No. of Pages : 2
[6181]-116

ic-
tat
B.E. (Computer Engineering)

7s
NATURAL LANGUAGE PROCESSING

3:4
(2019 Pattern) (Semester - VIII) (410252A) (Elective - V)

02 91
3:5
0
Time : 2½ Hours] [Max. Marks : 70

31
6/1 13
Instructions to the candidates:
1) All questions are compulsory.
0
2/2
.23 GP

2) Figures to the right indicate full marks.

E
80

Q1) a) What are generative models of language? Explain any one model in detail.[4]

8
C

23
b) Consider the following small corpus: [8]

ic-
16

tat
Training corpus:
8.2

7s
<s> I am from Pune </s>
.24

3:4
91
<s> I am a teacher </s>
49

3:5
<s> students are good and are from various cities </s>
30
31

<s> students from Pune do engineering </s>

01
02
2/2

Test data:
GP
6/1

<s> students are from Pune </s>

CE
80

8
Find the Bigram probability of the given test sentence.

23
.23

c) Explain in detail Latent Semantic Analysis for topic modelling (LSA).[6]

ic-
16

tat
OR
8.2

7s

Q2) a) Write short note on BERT. [4]

.24

3:4
91

b) Given a document-term matrix with the following counts: [6]

49

3:5
30

Document 1 Document 2 Document 3

31
01

Term 1 10 5 0
02
2/2

Term 2 2 0 8
GP
6/1

Term 3 1 3 6
CE
80

Calculate the TF-IDF score of “Term 1” in “Document 1”.

.23

c) Describe the Latent Dirichlet Allocation (LDA) algorithm and how it is

16

used for topic modeling? [8]

8.2
.24

P.T.O.
49
Q3) a) Describe the concept of Information Retrieval. Explain the significance

8
of Natural Language Processing in Information Retrieval. [4]

23
b) Explain reference resolution and conference resolution with example.[8]

ic-
tat
c) What is Cross-Lingual information Retrieval, and how is it used in Natural
Language Processing? Provide an example. [6]

7s
OR

3:4
02 91
Q4) a) Explain the concept of the Vector Space Model, and describe how it is

3:5
used in Information Retrieval. [6]

0
31
b) 6/1 13
Describe entity extraction and relation extraction with the help of examples.[8]
c) What is Named Entity Recognition (NER)? Describe the various metrics
0
2/2
.23 GP

used for evaluation. [4]

E
80

8
Q5) a) List the tools available for the development of NLP applications? Write
C

23
the features of any 3 tools. [7]

ic-
b) Describe in detail the Lesk algorithm and Walker’s algorithm for word
16

tat
sense disambiguation. [10]
8.2

7s
OR
.24

Q6) a)
3:4
Explain the following lexical knowledge networks? [10]
91
49

3:5
i) WordNet
30
31

ii) Indo WordNet

01
02

iii) VerbNets
2/2

iv) PropBank
GP
6/1

v) Treebanks
CE
80

b) Write Python code using NLTK library to split the text into tokens using

8
23
whitespace, punctuation-based and default tokenization methods. [7]
.23

ic-
16

tat
Q7) a) Explain three stages of Question Answering system with neat diagram.[7]
8.2

7s

b) Explain Rule based Machine Translation and Statistical Machine Translation

.24

3:4

(SMT) with suitable diagrams and example. [10]

91
49

3:5

OR
30
31

Q8) a) Describe following NLP applications: [10]

01
02

i) Text Entailment
2/2

ii) Dialog and Conversational Agents

GP
6/1

b) Explain Natural Language Generation with reference architecture. [7]

CE
80


.23
16
8.2
.24

[6181]-116
[6154]-383 2
49