WorksheetsNLP_6_7
Total questions: 11
Worksheet time: 6mins
Name
Class
Date
1.
Which of the following is NOT a type of word embedding technique?
a)
a) Word2Vec
b)
b) GLoVE
c)
c) Bag of Words
d)
d) Skip-gram
2.
What is the purpose of the Continuous Bag of Words (CBoW) model?
a)
To predict the context words given a target word
b)
b) To predict the target word given a set of context words
c)
c) To generate new text based on a given set of words
d)
To predict the next word given pervious words
3.
What is the difference between static embeddings and contextualized embeddings?
a)
Static embeddings are trained on a specific task, while contextualized embeddings are trained on a general task
b)
b) Static embeddings are the same as binary bag of words
c)
c) Static embeddings are fixed for all instances of a word, while contextualized embeddings vary depending on the context of the word
d)
Static embeddings are generated using CBoW while contextualized embedding are based on skip-grams
4.
What is the purpose of word embeddings?
a)
To capture the meaning of words in a numeric format
b)
To create hand-crafted features for machine learning models
c)
To collect specially-designed data for machine learning models
d)
to compress high dimensional sparse representation of words into a compact form
5.
What is the advantage of language models over most other machine learning models?
a)
They need hand-crafted features and specially-collected data
b)
b) They can be trained on running text in a self-supervised manner
c)
c) They require a small corpus of text data
d)
d) They are much smarter
6.
What type of loss function used in both CBOW and Skip-Gram models?
a)
A) sigmoid
b)
B) They exclusively use a mean squared error loss function.
c)
C) The loss functions prioritize syntactic accuracy over semantic meaning.
d)
D) They employ softmax functions
e)
E) Loss functions in these models are irrelevant as long as the embeddings are accurate.
7.
What is the dimension of the softmax layer in the CBoW model
a)
one as this is a binary classification
b)
Vocabulary size
c)
equals the embedding dimension used
d)
the same as the dimension of the weight matrix
8.
What is the role of Cross-Entropy loss in CBOW and Skip-Gram models?
a)
A) Balancing the weight distribution across different layers of the neural network.
b)
B) Reducing the impact of less frequent words in the vocabulary.
c)
C) Maximizing the probability of the target word given its context (or vice versa).
d)
D) Simplifying the model to work with binary classification tasks.
9.
How does the Skip-Gram model in word embeddings operate?
a)
A) By predicting surrounding context words from a given target word.
b)
B) By converting each word into a fixed numerical vector irrespective of context.
c)
C) By using a sequence of words to predict the next word in a sentence.
d)
D) By skipping irrelevant words in a sentence to focus on key terms.
10.
What distinguishes the Continuous Bag of Words (CBOW) model in word embeddings?
a)
A) It predicts a target word based on a set of context words surrounding it.
b)
B) It transforms words into binary representations for classification tasks.
c)
C) CBOW is used exclusively for speech recognition.
d)
D) It predicts context words from a target word.
11.
What is the primary basic task of a Language Model in NLP?
a)
A) To accurately translate text between different languages.
b)
B) To predict the likelihood of a sequence of words
c)
C) To classify text into predefined categories.
d)
D) to summarize text
100 %
