NLP Using Deep Learning MCQs Solution | TCS Fresco Play | Fresco Play | TCS
Make an effort to understand these solutions and apply them to your Hands-On difficulties. (It is not advisable that copy and paste these solutions).
All Question of the MCQs Present Below for Ease Use Ctrl + F with the question name to find the Question. All the Best!
1. For the window size two, what would be the maximum number of target words that can be sampled for skip gram model?
2
*4
1
3
2. Which of the following model predicts if a word is a context of another word or not?
GloVe model
*Negative sampling
CBOW model
Skip gram model
3. Which of the following model tries to predict the context word based on the target?
LSTM
CBOW model
GloVe model
*Skip gram model
4. Which layer of the Skip-gram model has an actual word embedding representation?
*Hidden layer
5. Which of the following activations is used in the CBOW model in its final layer to learn word embeddings?
Relu activation
*Softmax activation
Sigmoid activation
Leaky Relu activation
6. Which of the following option is the drawback of representing text as one hot encoding?
Leads to out of memory error
Not a valid representation for the neural network to process
*No contextual relationship
Impossible to uniquely encode all the words in the text
7. Which of the following option/options is/are the advantages of learning word embeddings?
Retain contextual relationship
reduce computation time
Represent words in reduced dimension space
*All of the options
8. Which of the following model needs fewer training samples to learn the word embeddings?
*Negative sampling
Skip gram model
CBOW model
GloVe model
9. Similar words tend to have similar word embeddings representations.
Depends on the corpus that is used to train
10. Which of the following model tries to predict the target word based on the context?
Negative sampling
GloVe model
Skip-gram Model
*CBOW model
11. Which of the following function in Keras is used to add the embedding layer to the model?
Keras.layers.Lookup()
*Keras.layers.Embedding()
Keras.layers.Sequential()
Keras.layers.Hidden(
12. Which of the following model learns the word embeddings based on the co-occurrence of the words in the corpus?
CBOW model
Skip gram model
Negative sampling
*GloVe model
13. Which of the following values is passed to sg parameter of gensim Word2Vec() to generate word vectors using CBOW gram model?
*1
3
2
0
14. Which of the following values is passed to sg parameter of gensim Word2Vec() to generate word vectors using CBOW gram model?
True Error
3
False
2
15. Which of the following values is passed to sg parameter of gensim Word2Vec() to generate word vectors using skip gram model?
3
1
2
*0
16. Which of the following metrics uses the dot product of two vectors to determine the similarity?
Jaccard similarity
Euclidean distance
Manhattan distance
*Cosine distance
17. Which of the following algorithm takes into account the global context of the word to generate word vectors?
Negative sampling
CBOW model
*GloVe model
Skip gram model
18. Which of the following model does not use the activation function to generate word embeddings?
*GloVe model
Skip gram model
CBOW model
Negative sampling
19. Which of the following is the constructor used in gensim to generate word vectors?
*Word2Vec()
KeyedVectors()
SkipGram()
Doc2Vec()
20. Which of the following models use co-occurrence matric to generate word vectors?
Skip gram model
CBOW model
Negative sampling
*GloVe model
21. Which of the following criteria is used by GloVe model to learn the word embeddings?
Maximize the distance between the vectors of two co-occurring words
Reduce the similarity between two-word vectors appearing in the same context
reduce the loss function value for predicting the co-occurring word for a given word
*Reduce the difference between the similarity of two-word vectors and their co-occurrence value
22. Which of the following model learn the word embeddings based on the co-occurrence of the words in the corpus?
CBOW model
Negative sampling
Skip gram model
*GloVe model
23. What is meant by beam width in Beam search algorithm?
The length of the translated sentence
The number of layers in the decoder
The vocabulary size
*The maximum number of words to be sampled at a time by decoder
24. The functionality of encoder in an encoder-decoder network for machine translation is __________.
*To generate unique encoding for the input sentence
To predict the next word in the sentence
To learn word vectors for each words in the input sentence
To generate translated words
Post a Comment