wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

Natural Language Processing(NLP)

Total questions: 44

Worksheet time: 22mins

Name
Class
Date
1.

What does NLP stand for?

a)

a) Natural Language Programming

b)

b) Natural Linguistic Processing

c)

c) Natural Language Processing

d)

d) Native Language Parser

2.

Which of the following is a major goal of NLP?

a)

a) Compiling programming languages

b)

b) Making computers understand human language

c)

c) Creating hardware interfaces

d)

d) None of the above

3.

Which year did Alan Turing propose the Turing Test?

a)

a) 1943

b)

b) 1950

c)

c) 1960

d)

d) 1975

4.

The first significant NLP system was developed for:

a)

a) Translation

b)

b) Sentiment analysis

c)

c) Voice control

d)

d) Summarization

5.

What was the name of the first machine translation system?

a)

a) ELIZA

b)

b) ALPAC

c)

c) Georgetown Experiment

d)

d) Watson

6.

Which programming language is commonly used for modern NLP applications?

a)

a) Java

b)

b) Python

c)

c) C++

d)

d) COBOL

7.

NLP is a subfield of which broader field?

a)

a) Robotics

b)

b) Artificial Intelligence

c)

c) Networking

d)

d) Databases

8.

Which of the following is not a common NLP task?

a)

a) Parsing

b)

b) Tokenization

c)

c) Object detection

d)

d) Named Entity Recognition

9.

Which NLP task involves identifying people, places, and organizations in text?

a)

a) POS tagging

b)

b) Named Entity Recognition

c)

c) Parsing

d)

d) Tokenization

10.

Which NLP application converts voice to text?

a)

a) Speech synthesis

b)

b) Speech recognition

c)

c) Speech compression

d)

d) Signal filtering

11.

Which is a real-world example of NLP?

a)

a) Face recognition

b)

b) Google Translate

c)

c) AutoCAD

d)

d) ImageNet

12.

Which is used for language generation in NLP?

a)

a) Classification

b)

b) Text summarization

c)

c) POS tagging

d)

d) Parsing

13.

Sentiment analysis is used in which of the following domains?

a)

a) Customer reviews

b)

b) Weather forecasting

c)

c) Network routing

d)

d) DNA sequencing

14.

What is tokenization in NLP?

a)

a) Assigning labels

b)

b) Splitting text into smaller parts

c)

c) Finding nouns

d)

d) Compressing sentences

15.

What is a 'phrase' in NLP?

a)

a) A full paragraph

b)

b) A group of words that act as a unit

c)

c) A single noun

d)

d) A punctuation mark

16.

Lexical ambiguity occurs when:

a)

a) A sentence has multiple meanings

b)

b) A word has multiple meanings

c)

c) Grammar is incorrect

d)

d) There is a spelling mistake

17.

Syntactic ambiguity is caused by:

a)

a) Multiple spellings

b)

b) Lack of data

c)

c) Sentence structure allowing different interpretations

d)

d) Slang words

18.

Which is an example of lexical ambiguity?

a)

a) “I saw the man with a telescope.”

b)

b) “Bank” meaning financial institution or river bank

c)

c) “The old man the boat.”

d)

d) “Flying planes can be dangerous.”

19.

Which is the first step in an NLP pipeline?

a)

a) Stemming

b)

b) Tokenization

c)

c) Parsing

d)

d) Classification

20.

Which is not a step in standard NLP pipelining?

a)

a) Tokenization

b)

b) POS tagging

c)

c) Firewall filtering

d)

d) Named Entity Recognition

21.

What does language modeling try to do?

a)

a) Translate text

b)

b) Predict the next word

c)

c) Remove stopwords

d)

d) Count characters

22.

Which of these is a type of language model?

a)

a) CNN

b)

b) Naive Bayes

c)

c) Bigram
(N-Gram)

d)

d) Ridge regression

23.

What is a unigram model?

a)

a) Considers 1 word at a time

b)

b) Uses 2-word pairs

c)

c) Based on paragraphs

d)

d) Ignores punctuation

24.

Which model considers word order and previous words?

a)

a) Unigram

b)

b) Bigram/Trigram

c)

c) Bag of Words

d)

d) TF-IDF

25.

POS stands for:

a)

a) Probability of Syntax

b)

b) Part-of-Speech

c)

c) Prediction of Structure

d)

d) Parsing of Sentences

26.

What does a POS tagger do?

a)

a) Tags parts of a car

b)

b) Assigns grammatical roles to words

c)

c) Removes stopwords

d)

d) Summarizes text

27.

Which of these is a valid POS tag?

a)

a) NNP

b)

b) TTT

c)

c) SNT

d)

d) VBS

28.

POS tagging is an example of:

a)

a) Classification

b)

b) Clustering

c)

c) Regression

d)

d) Compression

29.

NER stands for:

a)

a) Named External Routing

b)

b) Natural Entity Reduction

c)

c) Named Entity Recognition

d)

d) Name Extension Registry

30.

NER identifies which of the following?

a)

a) Words

b)

b) Sentences

c)

c) People, Places, Organizations

d)

d) Verbs

31.

Which NLP task comes after tokenization and POS tagging in a pipeline?

a)

a) Machine translation

b)

b) Text summarization

c)

c) Named Entity Recognition

d)

d) Spell checking

32.

"Barack Obama" would be labeled in NER as:

a)

a) Date

b)

b) Organization

c)

c) Location

d)

d) Person

33.

HMM stands for:

a)

a) Hidden Markov Model

b)

b) Hybrid Memory Model

c)

c) Hierarchical Model Maker

d)

d) High Memory Map

34.

CRFs are used for:

a)

a) Random predictions

b)

b) Single word classification

c)

c) Sequence labeling

d)

d) Speech synthesis

35.

Which algorithm is used to decode CRFs?

a)

a) Forward algorithm

b)

b) Viterbi algorithm

c)

c) Naive Bayes

d)

d) TF-IDF

36.

Maximum Entropy is also known as:

a)

a) Naive Bayes

b)

b) Logistic Regression

c)

c) Support Vector

d)

d) Decision Tree

37.

MaxEnt models assume:

a)

a) Everything is independent

b)

b) All features are equally important

c)

c) Least biased outcome given known facts

d)

d) Sequence dependence

38.

What do CRFs solve better than HMMs?

a)

a) Memory usage

b)

b) Sequence alignment

c)

c) Label bias problem

d)

d) Feature selection

39.

Which model gives globally best label sequence?

a)

a) MaxEnt

b)

b) HMM

c)

c) CRF

40.

Which would be best for POS tagging with label dependencies?

a)

a) MaxEnt

b)

b) CRFs

c)

c) TF-IDF

41.


What will be the output of the following code?

import spacy nlp = spacy.load("en_core_web_sm") doc = nlp("Apple is looking at buying a startup in the UK") for ent in doc.ents: print(ent.text, ent.label_)

a)

A.

Apple PERSON startup ORG UK LOC

b)

B.

Apple ORG UK GPE

c)

C.

Apple PRODUCT UK COUNTRY

d)

D.

Apple ORG startup GPE UK ORG

42.

What is the main purpose of smoothing in language modeling?

a)

A. To remove stop words

b)

B. To reduce sentence length

c)

C. To handle zero probabilities for unseen events

d)

D. To increase the speed of the algorithm

43.

What does the Good-Turing method adjust?

a)

A. The maximum frequency only

b)

B. The frequency of observed n-grams

c)

C. The probability mass of unobserved events

d)

D. Only bigram counts

44.

What does Kneser-Ney smoothing improve over other techniques?

a)

A. Memory usage

b)

B. Predicting common words

c)

C. Estimating rare or unseen n-grams by considering their diversity of contexts

d)

D. Assigning highest probability to stopwords