Home - Ugc Net Computer Science - Practice Questions - Artificial Intelligence - Natural Language Processing

Artificial Intelligence - Natural Language Processing Online Exam Quiz

Important questions about Artificial Intelligence - Natural Language Processing. Artificial Intelligence - Natural Language Processing MCQ questions with answers. Artificial Intelligence - Natural Language Processing exam questions and answers for students and interviews.

1. Ambiguity can appear in which of the following steps/tasks?

Options

A : Tokenization

B : Language Understanding

C : Sentence Segmentaion

D : All of these

2. One of the main challenges of NLP is _____

Options

A : Ambiguity of sentences

B : Handling toeniztion

C : Usage of non-standard English

D : New senses of a word

3. Which of the following doesn't require application of Natural Language Processing algorithms?

Options

A : Classifying spam emails from good ones

B : Classifying images of scanned documents as "hand-written" or "printed" documents

C : Automatically generating captions for images

D : Building a sentiment analyzer for tweets on Twitter.

4. Which one is not an example of neologisms:

Options

A : Cryptocurrency

B : Blogging

C : Friendship

D : Googling

5. Which of the following sentence contains a ditransitive verb usage?

Options

A : Maureen gave Dan the pencil

B : She lied

C : That pumpkin pie smells delicious

D : The dog chased the cats

6. If first corpus has TTR 1 = 0.013 and second corpus has TTR 2 = 0.13, where TTR 1 and TTR 2 represents type/token ratio in first and second corpus respectively, then

Options

A : First corpus has more tendency to use different words.

B : Second corpus has more tendency to use different words.

C : Both A and B

D : None of these

7. Which of the following are instances of stemming? (as per Porter Stemmer) 1. are → be 2. plays → play 3. saw → s 4. university → univers

Options

A : 1 and 2

B : 2 and 3

C : 1 and 3

D : 2 and 4

8. Which of the following is/are true for English Language? 1. Lemmatization works only on inflectional morphemes and Stemming works only on derivational morphemes. 2. The outputs of lemmatization and stemming for the same word might differ. 3. Output of lemmatization are always real words 4. Output of stemming are always real words

Options

A : 1 and 2

B : 2 and 3

C : 3 and 4

D : 1 and 4

9. As per Zipf's law, the correct statement about a corpus is:

Options

A : 10th most common word will occur with 10 times the frequency of the 100th most common word.

B : 100th most common word will occur with 10 times the frequency of the 10th most common word

C : Frequency of a word is directly proportional to its position in the ranked list.

D : None of these

10. Which one is not related to the concept of decision tree algorithm:

Options

A : PCA

B : ID3

C : Random Forest

D : C4.5

11. Word segmentation is mostly used when:

Options

A : Hyphens are present

B : Multiple alphabets intermingled

C : Long sentence

D : No space between words

12. What is the valid range of type-token ratio of any text corpus?

Options

A : TTR ∈ (0,1] (excluding zero)

B : TTR ∈ [0,1]

C : TTR ∈ [-1,1]

D : TTR ∈ [0,+∞] (any non-negative number)

13. Find the type-token ratio for following sentence, But what are thoughts? Well, we all have them. They are variously described as ideas, notions, concepts, impressions, perceptions, views, beliefs, opinions, values, and so on. At times they are brief, coming and going in an instant.

Options

A : 1.0

B : 37/33

C : 33/37

D : No space between words

14. In the sentence, "In Delhi I took my hat off. But I can't put it back on.", total number of word tokens and word types are:

Options

A : 14, 13

B : 13, 14

C : 15, 14

D : 14, 15

15. Consider the following corpus C 1 of 4 sentence. What is the total count of unique bi-grams for which the likelihood will be estimated? Assume we do not perform any pre-processing. Today is Nayan's birthday she loves ice cream she is also fond of cream cake we will celebrate her birthday with ice cream cake

Options

A : 24

B : 28

C : 27

D : 23

16. A 4-gram model is a ________ order Markov Model.

Options

A : Constant

B : Five

C : Four

D : Three

17. Arrange the words "blueberry, cranberry, raspberry, strawberry" in descending order, based on the frequency of their occurrence in the Google Books n-grams. The Google Books n-gram viewer i available at https://books.google.com/ngrams.

Options

A : raspberry, strawberry, blueberry, cranberry

B : blueberry, cranberry, raspberry, strawberry

C : strawberry, raspberry, cranberry, blueberry

D : None of the above

18. For the string 'mash', identify which of the following set of strings have a Levenshtein distance of 1

Options

A : smash, mas, lash, mushy, hash

B : bash, stash, lush, flash, dash

C : smash, mas, lash, mush, ash

D : None of the above

19. Assume that we modify the costs incurred for operations in calculating Levenshtein distance, such that both the insertion and deletion operations incur a cost of 1 each, while substitution incurs a cost of 2. Now, for the string 'lash' which of the following set of strings will have an edit distance of 1?

Options

A : ash, slash, clash, flush

B : flash, stash, lush, blush

C : slash, last, bash, ash

D : None of the above

20. Given a corpus C 2 , the Maximum Likelihood Estimation (MLE) for the bigram "dried berries" is 0.3 and the count of occurrence of the word "dried" is 580 for the same corpus C 2 , the likelihood of "dried berries" after applying add-one smoothing is 0.04. What is the vocabulary size of C 2 ?

Options

A : 3585

B : 3795

C : 4955

D : 3995

Ugc Net Computer Science - Practice Questions more Online Exam Quiz

Copyright © 2021
Exam-GK-MCQ-Questions.Com | Contact Us | Privacy Policy | Terms of Use | Sitemap | 0.025926113128662