Back to Subject

Unit 2 - Practice Quiz

INT344 50 Questions
0 Correct 0 Wrong 50 Left
0/50

1 What is the fundamental representation of a word in a Vector Space Model (VSM)?

A. A binary tree structure
B. A linked list
C. A vector of real numbers
D. A scalar integer

2 Which of the following is a primary advantage of dense word vectors over one-hot encoding?

A. They are easier to calculate manually
B. They are strictly binary
C. They use more memory
D. They capture semantic relationships

3 In the context of the Continuous Bag-of-Words (CBOW) model, what is the input to the neural network?

A. The entire document
B. The center word
C. A random noise vector
D. The context words

4 How is 'cosine similarity' calculated between two word vectors, A and B?

A. Sum of elements in A minus sum of elements in B
B. Euclidean distance between A and B
C. Dot product of A and B divided by the product of their magnitudes
D. Cross product of A and B

5 If two word vectors have a cosine similarity of 1, what does this imply?

A. The vectors are orthogonal
B. The words represent opposite meanings
C. The words are unrelated
D. The vectors point in exactly the same direction

6 Which architecture predicts the surrounding words given a center word?

A. Skip-gram
B. Latent Dirichlet Allocation
C. Principal Component Analysis
D. Continuous Bag-of-Words (CBOW)

7 What mathematical technique is commonly used to visualize high-dimensional word vectors in two dimensions?

A. Linear Regression
B. Principal Component Analysis (PCA)
C. Fourier Transform
D. Logistic Regression

8 In vector arithmetic for analogies, what result is expected for vector('King') - vector('Man') + vector('Woman')?

A. Queen
B. Princess
C. Monarch
D. Prince

9 What is the role of the 'window size' hyperparameter in CBOW?

A. It determines the number of dimensions in the vector
B. It sets the learning rate
C. It defines how many neighbors to consider as context
D. It determines the number of epochs

10 Why are vector space models useful for information retrieval/document search?

A. They work best with images
B. They allow exact keyword matching only
C. They eliminate the need for indexing
D. They can match queries to documents based on semantic similarity

11 When transforming word vectors from one language to another (e.g., English to French) using a linear mapping, what are we trying to learn?

A. A clustering algorithm
B. A binary classifier
C. A rotation matrix
D. A decision tree

12 In PCA, the first principal component is the direction that maximizes what?

A. The variance of the data
B. The error rate
C. The cosine similarity
D. The number of clusters

13 Which of the following best describes the 'bag-of-words' model assumption?

A. Dependencies between words are preserved
B. Word order is ignored, only frequency counts matter
C. Word order is critical for meaning
D. Grammar rules are strictly enforced

14 In the CBOW model, how are the input context vectors usually handled before passing to the hidden layer?

A. They are multiplied
B. They are averaged or summed
C. Only the first word is used
D. They are concatenated

15 What does a cosine similarity of 0 indicate between two word vectors?

A. They are opposite
B. They are identical
C. They are orthogonal (unrelated)
D. One is a scalar multiple of the other

16 Which loss function is typically minimized when aligning two vector spaces (X and Y) via a transformation matrix R?

A. Cross-entropy loss
B. Hinge loss
C. Frobenius norm of (XR - Y)
D. Accuracy score

17 Deep Learning vector models like Word2Vec are often referred to as:

A. Prediction-based embeddings
B. Hierarchical clusters
C. Count-based matrices
D. Sparse embeddings

18 If 'Apple' and 'Pear' are close in vector space, this indicates:

A. Morphological similarity
B. Syntactic similarity
C. Semantic similarity
D. Phonetic similarity

19 When visualizing word vectors, why can't we simply plot the 300-dimensional vectors directly?

A. Computers cannot store 300 dimensions
B. Human visual perception is limited to 2 or 3 dimensions
C. It would take too long to render
D. The vectors become binary

20 Which of the following is NOT a benefit of using Vector Space Models in Machine Translation?

A. Handling rare words via similarity
B. Improving alignment of synonyms
C. Guaranteeing grammatically perfect sentences
D. Mapping entire languages without parallel corpora (unsupervised)

21 In a Word2Vec model, the dimension of the hidden layer corresponds to:

A. The window size
B. The vocabulary size
C. The size of the word embedding vector
D. The number of training documents

22 To perform document search using word vectors, how might one represent a whole document?

A. By concatenating all vectors into one giant vector
B. By taking the average (centroid) of all word vectors in the document
C. By using the vector of the first word only
D. By summing the ASCII values of characters

23 What is the 'Curse of Dimensionality' in the context of NLP?

A. Having too few dimensions to represent meaning
B. The time it takes to train a model
C. Data becoming sparse and distance metrics becoming less meaningful in very high dimensions
D. The inability to use PCA

24 Which algebraic structure is used to transform word vectors from a source language space to a target language space?

A. A transformation matrix
B. A tensor of rank 3
C. A vector
D. A scalar

25 In PCA, what are 'eigenvalues' used for?

A. To label the axes
B. To determine the direction of axes
C. To calculate the dot product
D. To quantify the variance explained by each principal component

26 Which word pair would likely have the highest Euclidean distance in a well-trained vector space?

A. Computer - Sandwich
B. Car - Automobile
C. Frog - Toad
D. Happy - Joyful

27 The output layer of a standard CBOW model typically uses which activation function to generate probabilities?

A. ReLU
B. Tanh
C. Sigmoid
D. Softmax

28 What is the main limitation of using Euclidean distance for word vectors compared to Cosine similarity?

A. It cannot handle negative numbers
B. It is sensitive to the magnitude (length) of the vectors
C. It is computationally harder
D. It only works in 2D

29 Which concept explains why 'Paris' is to 'France' as 'Tokyo' is to 'Japan' in vector space?

A. Singular Value Decomposition
B. Linear substructures / Parallelism
C. One-hot encoding
D. Orthogonality

30 How does PCA reduce dimensions?

A. By removing words with fewer than 3 letters
B. By projecting data onto new axes that minimize information loss
C. By deleting the last 50 columns of data
D. By averaging all data points to zero

31 In the context of relationships between words, 'distributional semantics' suggests that:

A. Words are defined by their spelling
B. Words that appear in similar contexts have similar meanings
C. Words are unrelated entities
D. Words are defined by their dictionary definitions

32 When training CBOW, what is the 'target'?

A. The sentiment of the sentence
B. The part of speech
C. The next sentence
D. The center word

33 What happens to the vectors of synonyms (e.g., 'huge' and 'enormous') during training?

A. They move infinitely far apart
B. One replaces the other
C. They become orthogonal
D. They move closer together

34 If you want to visualize a 1000-word subset of your vocabulary using PCA, what is the shape of the input matrix?

A. 1000 x 2
B. 1000 x Dimension_of_Embedding
C. 2 x 2
D. Dimension_of_Embedding x 1000

35 In cross-lingual information retrieval, query translation can be achieved by:

A. Re-training the model from scratch
B. Using a dictionary lookup only
C. Ignoring the language difference
D. Multiplying the query vector by a transformation matrix

36 What is a 'context window'?

A. The graphical user interface
B. The time limit for training
C. The number of words before and after a target word
D. The software used to view the code

37 Which of the following is NOT a step in performing PCA?

A. Applying a Softmax function
B. Computing eigenvectors and eigenvalues
C. Standardizing the data
D. Calculating the covariance matrix

38 If a word vector has a magnitude of 1, it is called:

A. A sparse vector
B. A binary vector
C. A normalized vector
D. A complex vector

39 Which approach is generally faster to train: CBOW or Skip-gram?

A. They are exactly the same
B. CBOW
C. Skip-gram
D. Neither is trainable

40 To capture dependencies between words that are far apart in a sentence, one should:

A. Use one-hot encoding
B. Decrease the window size
C. Increase the window size
D. Set window size to 0

41 The 'Manifold Hypothesis' in NLP suggests that:

A. All words are equidistant
B. High-dimensional language data lies on a lower-dimensional manifold
C. Language is flat
D. Vectors must be 3D

42 When performing vector arithmetic for 'Paris - France + Italy', the result is likely closest to:

A. Rome
B. Pizza
C. Germany
D. London

43 What is the dimensionality of the transformation matrix R used to map a source space of dimension D to a target space of dimension D?

A. 2D x 2D
B. D x D
C. D x 1
D. 1 x D

44 Which vector operation is primarily used to measure the relevance of a document to a search query in VSM?

A. Cosine Similarity
B. Vector Addition
C. Vector Subtraction
D. Scalar Multiplication

45 Sparse vectors (like Bag-of-Words) are characterized by:

A. Mostly zero values
B. Complex numbers
C. Negative numbers only
D. Mostly non-zero values

46 Word embeddings capture which type of relationships?

A. Both syntactic and semantic
B. Only syntactic
C. Neither
D. Only semantic

47 Before applying PCA, it is standard practice to:

A. Square the data
B. Invert the data
C. Randomize the data
D. Mean-center the data

48 In the analogy 'A is to B as C is to D', which equation represents the relationship in vector space?

A. B / A = D / C
B. B A = D C
C. B + A = D + C
D. B - A = D - C

49 Why might we use PCA on word vectors before performing clustering?

A. To convert vectors to text
B. To remove noise and reduce computational cost
C. To translate the language
D. To increase the number of dimensions

50 Which technique allows checking if the transformation matrix between two languages is accurate?

A. Checking the accuracy of translation on a hold-out dictionary
B. Measuring the vector length
C. Checking if the matrix is square
D. Calculating the determinant
Previous MCQ
Unit 1
Next MCQ
Unit 3