Back to Subject

Unit 2: Vector Space Models - Practice Quiz

INT344 — Natural Language Processing 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 vector of real numbers
B. A binary tree structure
C. A linked list
D. A scalar integer

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

A. They eliminate the need for indexing
B. They work best with images
C. They allow exact keyword matching only
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 rotation matrix
B. A decision tree
C. A clustering algorithm
D. A binary classifier

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

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

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

A. Word order is ignored, only frequency counts matter
B. Dependencies between words are preserved
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 averaged or summed
B. Only the first word is used
C. They are multiplied
D. They are concatenated

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

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

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

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

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

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

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

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

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

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

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

A. Handling rare words via similarity
B. Guaranteeing grammatically perfect sentences
C. Improving alignment of synonyms
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 size of the word embedding vector
C. The number of training documents
D. The vocabulary size

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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 averaging all data points to zero
D. By deleting the last 50 columns of data

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

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

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

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

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

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

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

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

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

36 What is a 'context window'?

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

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

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

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

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

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

A. Skip-gram
B. CBOW
C. They are exactly the same
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. Set window size to 0
C. Increase the window size
D. Decrease the window size

41 The 'Manifold Hypothesis' in NLP suggests that:

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

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

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

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. 1 x D
C. D x 1
D. D 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. Scalar Multiplication
C. Vector Subtraction
D. Vector Addition

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

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

46 Word embeddings capture which type of relationships?

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

47 Before applying PCA, it is standard practice to:

A. Mean-center the data
B. Invert the data
C. Randomize the data
D. Square 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 translate the language
C. To remove noise and reduce computational cost
D. To increase the number of dimensions

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

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