Natural Language Processing Questions and Answers (Set 2 of 8 Ques)

1. State whether True or False: Word2Vec is a neural network model used to convert input text to vector notations.

Answer: True

2. Which of the following are true regarding Word2Vec?

a. The architecture of Word2Vec model is a 2 layer neural network
b. The skip gram model is a RNN model 
c. Both CBOW and Skip-gram are shallow neural network models
d. All of the above

Answer: A and C

3. The network which traverses from output layer to input layer and hidden layer to improve the model is called ___.

a. Perceptron
b. Multi-layered Perceptron 
c. Self organizing map 
d. Recurrent neural network 

Answer: D: Recurrent neural network 

4. LSTM network is suitable for processing long sequences of data.

a. True
b. False 

Answer: True 

5. How to solve the vanishing gradient problem of RNN?

a. Feedforward Neural Network 
b. Long Short Term Memory
c. Convolutional Neural Network 
d. None of the above.

Answer: Long Short Term Memory

6. Which of the following statement is incorrect?

a. Stemming is the process of reducing a word to its stem or root format.
b. In stemming the suffixes "ing" and "ed" can be dropped off and 'ies' can be replaced by 'y'.
c. Lemmatization is a technique which is used to reduce words to a normalized form.
d. The result of stemming is always a proper word.

Answer: D 

7. Multiple Choice Correct
Which of the Python packages are used to implement Lemmatization?

a. WordNet Lemmatizer 
b. TextBlob
c. Standard CoreNLP 
d. TreeTagger

Answer: All of the option.

8. BLEU score is a metric used in NLP to evaluate the sentence generated at the output against that of the sentence given at the input.

a. True 
b. False 

Answer: A (True)

Tags: Natural Language Processing,