2/18/24, 9:22 PM Quiz 2: Natural Language Processing (S1-23_DSECLZG530)

Quiz 2
Due Feb 19 at 19:00
Points 10
Questions 10
Available Feb 18 at 19:00 - Feb 19 at 19:00 24 hours
Time Limit 60 Minutes

Instructions
Quiz 2

Attempt History
Attempt Time Score
LATEST Attempt 1 29 minutes 9 out of 10

 Correct answers will be available Feb 21 at 0:00 - Apr 30 at 0:00.

Score for this quiz: 9 out of 10

What is t-SNE?

a non-linear dimensionality reduction technique

a linear transformation that allows us to solve analogies on word vectors

an open-source sequence modeling library

a supervised learning algorithm for learning word embeddings


Question 2
1 / 1 pts

In the word2vec algorithm,you estimate P(t/c),where t is the target word and c is a context
word.How are t and c chosen from the training set? Pick the best answer

https://bits-pilani.instructure.com/courses/2546/quizzes/4835 1/4
2/18/24, 9:22 PM Quiz 2: Natural Language Processing (S1-23_DSECLZG530)

c is the sequence of all words in the sentence before t.

c and t are chosen to be nearby words

c is the one word that comes immediately before t.

c is sequence of several words immediately before t.


Question 3
1 / 1 pts

You have trained word embeddings using a text dataset of m1 words .You are considering using
these word embeddings for a language task,for which you have a seperate labeled dataset of m2
words.Keeping in mind that using word embeddings is a form of transfer learning under which of
these circumstances would you expect the word embeddings to be helpful?

m1>>m2

none

m1=m2

m1<<m2


Question 4
1 / 1 pts

Which algorithm is used for solving temporal probabilistic reasoning?

Depth-first search

Hill-climbing search

Breadth-first search

Hidden markov model


Question 5
1 / 1 pts

Which algorithm works by first running the standard forward pass to compute?

HMM

Modified smoothing

Smoothing

Depth-first search algorithm

https://bits-pilani.instructure.com/courses/2546/quizzes/4835 2/4
2/18/24, 9:22 PM Quiz 2: Natural Language Processing (S1-23_DSECLZG530)


Question 6
1 / 1 pts

In POS tagging problem, what is the output of Viterbi algorithm?

Probability of word sequence given a particular tag sequence

Probability of the best tag sequence given a word sequence

None of the above

Optimal transition and observation probabilities for HMM


Question 7
1 / 1 pts

What type of ambiguity exists in the word sequence “Time flies”?

Phonological

Semantic

Anaphoric

Syntactic


Question 8
1 / 1 pts

How many noun phrases are there in the following sentence " The thief robbed the apartment"?


IncorrectQuestion 9
0 / 1 pts

Which of the following are demerits of top down parser?

none

inefficient

https://bits-pilani.instructure.com/courses/2546/quizzes/4835 3/4
2/18/24, 9:22 PM Quiz 2: Natural Language Processing (S1-23_DSECLZG530)

Slow speed

It is hard to implement


Question 10
1 / 1 pts

Many words have more than one meaning; we have to select the meaning whichmakes the most
sense in context this can be resolved by_____________

Fuzzy Logic

All

Shallow Semantic Analysis

Word Sense Disambiguation

Quiz Score: 9 out of 10

https://bits-pilani.instructure.com/courses/2546/quizzes/4835 4/4
18/02/2024, 21:29 Quiz 2: Natural Language Processing (S1-23_DSECLZG530)

Quiz 2
Due Feb 19 at 19:00
Points 10
Questions 10
Available Feb 18 at 19:00 - Feb 19 at 19:00 24 hours
Time Limit 60 Minutes

Instructions
Quiz 2

Attempt History
Attempt Time Score
LATEST Attempt 1 7 minutes 10 out of 10

 Correct answers will be available Feb 21 at 0:00 - Apr 30 at 0:00.

Score for this quiz: 10 out of 10

What is t-SNE?

https://bits-pilani.instructure.com/courses/2546/quizzes/4835 1/5
18/02/2024, 21:29 Quiz 2: Natural Language Processing (S1-23_DSECLZG530)

an open-source sequence modeling library

a non-linear dimensionality reduction technique

a supervised learning algorithm for learning word embeddings

a linear transformation that allows us to solve analogies on word vectors


Question 2
1 / 1 pts

In the word2vec algorithm,you estimate P(t/c),where t is the target word and c is a context word.How are t and c chosen from the training set? Pick
the best answer

c and t are chosen to be nearby words

c is the one word that comes immediately before t.

c is sequence of several words immediately before t.

c is the sequence of all words in the sentence before t.


Question 3
1 / 1 pts

You have trained word embeddings using a text dataset of m1 words .You are considering using these word embeddings for a language task,for
which you have a seperate labeled dataset of m2 words.Keeping in mind that using word embeddings is a form of transfer learning under which of
these circumstances would you expect the word embeddings to be helpful?

m1>>m2

https://bits-pilani.instructure.com/courses/2546/quizzes/4835 2/5
18/02/2024, 21:29 Quiz 2: Natural Language Processing (S1-23_DSECLZG530)

none

m1<<m2

m1=m2


Question 4
1 / 1 pts

Which algorithm is used for solving temporal probabilistic reasoning?

Breadth-first search

Depth-first search

Hidden markov model

Hill-climbing search


Question 5
1 / 1 pts

Which algorithm works by first running the standard forward pass to compute?

Modified smoothing

Depth-first search algorithm

Smoothing

HMM


Question 6
1 / 1 pts
https://bits-pilani.instructure.com/courses/2546/quizzes/4835 3/5
18/02/2024, 21:29 Quiz 2: Natural Language Processing (S1-23_DSECLZG530)

In POS tagging problem, what is the output of Viterbi algorithm?

Optimal transition and observation probabilities for HMM

None of the above

Probability of word sequence given a particular tag sequence

Probability of the best tag sequence given a word sequence


Question 7
1 / 1 pts

What type of ambiguity exists in the word sequence “Time flies”?

Syntactic

Anaphoric

Phonological

Semantic


Question 8
1 / 1 pts

How many noun phrases are there in the following sentence " The thief robbed the apartment"?

https://bits-pilani.instructure.com/courses/2546/quizzes/4835 4/5
18/02/2024, 21:29 Quiz 2: Natural Language Processing (S1-23_DSECLZG530)


Question 9
1 / 1 pts

Which of the following are demerits of top down parser?

none

Slow speed

It is hard to implement

inefficient


Question 10
1 / 1 pts

Many words have more than one meaning; we have to select the meaning whichmakes the most sense in context this can be resolved
by_____________

Shallow Semantic Analysis

Word Sense Disambiguation

Fuzzy Logic

All

Quiz Score: 10 out of 10

https://bits-pilani.instructure.com/courses/2546/quizzes/4835 5/5