Back to Subject

Unit 3: Natural Language Processing with Probabilistic Models - Practice Quiz

INT344 — Natural Language Processing 50 Questions
0 Correct 0 Wrong 50 Left
0/50

1 What is the primary goal of calculating Minimum Edit Distance?

A. To calculate the probability of a word appearing in a sentence
B. To quantify the dissimilarity between two strings by counting operations
C. To find the longest common subsequence between two strings
D. To generate word embeddings for a neural network

2 Which of the following operations is NOT typically used in the Levenshtein distance algorithm?

A. Insertion
B. Deletion
C. Substitution
D. Transposition

3 In the context of dynamic programming for edit distance, if source[i] equals target[j], what is the cost of substitution?

A. 1
B. 2
C. 0
D. Infinity

4 What is the Minimum Edit Distance between the strings 'cat' and 'cut'?

A. 3
B. 1
C. 0
D. 2

5 How does an autocorrect system typically identify candidate words for a misspelled word?

A. By using the longest word in the dictionary
B. By choosing words that start with the same letter only
C. By finding words within a certain edit distance threshold
D. By selecting random words from the dictionary

6 Which algorithm is commonly used to efficiently calculate the Minimum Edit Distance?

A. K-Means Clustering
B. Gradient Descent
C. Depth-First Search
D. Dynamic Programming

7 In Part of Speech (POS) tagging, what is the 'Hidden' component in a Hidden Markov Model?

A. The words in the sentence
B. The punctuation marks
C. The transition probabilities
D. The Part of Speech tags

8 What does the Markov Assumption state in the context of Markov Chains?

A. The future state depends on the hidden emissions
B. The future state depends only on the current state
C. The future state is independent of the current state
D. The future state depends on all past states

9 What are 'Transition Probabilities' in an HMM?

A. The probability of generating a specific word given a tag
B. The probability of a sentence starting with a specific word
C. The probability of a word being misspelled
D. The probability of moving from one POS tag to another

10 What are 'Emission Probabilities' in an HMM used for POS tagging?

A. P(tag|word)
B. P(word|tag)
C. P(tag|previous_tag)
D. P(word|previous_word)

11 Which algorithm is used to find the most likely sequence of hidden states (POS tags) given a sequence of observations?

A. The Backward Algorithm
B. The Forward Algorithm
C. The Edit Distance Algorithm
D. The Viterbi Algorithm

12 A text corpus is:

A. A large, structured set of texts used for statistical analysis
B. A set of rules for grammar
C. A software used for autocorrection
D. A dictionary of word definitions

13 In an N-gram language model, what is 'N'?

A. The number of words in the sequence considered for probability
B. The number of words in the sentence
C. The number of hidden states
D. The dimension of the word embedding

14 Which assumption simplifies the calculation of N-gram probabilities?

A. The probability depends on the entire sentence history
B. All words have equal probability
C. Words are independent of each other
D. The probability of a word depends only on the previous N-1 words

15 How is the probability of a bigram P(w2 | w1) calculated from a corpus?

A. Count(w1) / Count(w2)
B. Count(w1) * Count(w2)
C. Count(w1, w2) / Count(w2)
D. Count(w1, w2) / Count(w1)

16 What is the main problem with N-gram models when N is very large?

A. The vocabulary size decreases
B. The model becomes too simple
C. Data sparsity (many sequences have zero counts)
D. The context window becomes too small

17 What technique is used to handle N-grams that have zero probability in the training data?

A. Tagging
B. Filtering
C. Pruning
D. Smoothing (e.g., Laplace Smoothing)

18 In Laplace (Add-1) smoothing, what is added to the denominator?

A. The total word count
B. 1
C. The vocabulary size (V)
D. The number of sentences

19 What does an autocomplete system try to maximize?

A. P(next_word | previous_words)
B. P(previous_words | next_word)
C. The edit distance between words
D. The length of the sentence

20 A Trigram model looks at how many previous words to predict the next word?

A. 1
B. 3
C. 0
D. 2

21 One-hot encoding of words results in vectors that are:

A. Sparse and high-dimensional
B. Dense and high-dimensional
C. Sparse and low-dimensional
D. Dense and low-dimensional

22 What is a major limitation of one-hot encoding for words?

A. It cannot represent rare words
B. It requires a neural network
C. It is difficult to compute
D. It does not capture semantic similarity between words

23 Word embeddings typically represent words as:

A. Dense vectors of real numbers
B. Integers
C. Strings
D. Sparse binary vectors

24 Which metric is commonly used to measure the similarity between two word embedding vectors?

A. Perplexity
B. Edit Distance
C. Cosine Similarity
D. Jaccard Index

25 The Word2Vec model 'Skip-gram' architecture tries to predict:

A. The POS tag of the word
B. The next sentence
C. The target word given the context words
D. The context words given the target word

26 The Word2Vec model 'CBOW' (Continuous Bag of Words) architecture tries to predict:

A. The context words given the target word
B. The target word given the context words
C. The part of speech
D. The document topic

27 What famous algebraic property is often cited to demonstrate the semantic capability of word embeddings?

A. Paris - France = Germany
B. Apple + Orange = Fruit
C. King - Man + Woman = Queen
D. Fast + Slow = Speed

28 In the 'Noisy Channel Model' for spelling correction, P(x|w) represents:

A. The probability of x being a valid word
B. The probability that the user meant w but typed x
C. The probability of the word w appearing in the corpus
D. The probability of typing x given the intended word w

29 When building an HMM for POS tagging, the sum of probabilities of all outgoing transitions from a single state must equal:

A. The number of observations
B. 0
C. The number of states
D. 1

30 What is 'Perplexity' in the context of Language Models?

A. The number of parameters in the model
B. The time taken to train the model
C. The size of the vocabulary
D. A measure of how well a probability model predicts a sample

31 Why do we use Log Probabilities instead of raw probabilities in N-gram calculations?

A. To make numbers larger
B. To avoid arithmetic underflow
C. To increase perplexity
D. To handle negative numbers

32 Which of the following describes the 'Start' token (<s>) in N-gram models?

A. It represents an unknown word
B. It gives context for the first word in the sentence
C. It indicates the end of a sentence
D. It is used for punctuation

33 What represents the 'Observations' in a POS HMM?

A. The sequence of words in the text
B. The sequence of tags
C. The transition matrix
D. The initial state probabilities

34 In Minimum Edit Distance, the 'backtrace' step is used to:

A. Determine the actual sequence of operations (alignment)
B. Sum the rows
C. Initialize the matrix
D. Calculate the cost

35 Which token is typically used to replace words not found in the training vocabulary?

A. <UNK>
B. <START>
C. <NULL>
D. <END>

36 A 'Unigram' model assumes that:

A. Words depend on the previous word
B. Words are independent of context
C. Words depend on the previous two words
D. Words depend on the grammar

37 The dimensionality of a Word2Vec embedding vector is typically chosen by:

A. The number of unique characters
B. The length of the sentence
C. The system designer (hyperparameter)
D. The size of the vocabulary

38 In the equation P(tag|word) ∝ P(word|tag) * P(tag), what is P(tag)?

A. Prior probability
B. Emission probability
C. Likelihood
D. Posterior probability

39 If we want to build a spell checker, which probability do we want to maximize according to Bayes' theorem?

A. P(typo | correction)
B. P(typo)
C. P(correction)
D. P(correction | typo)

40 Which type of language model suffers most from the 'curse of dimensionality'?

A. High-order N-gram model (e.g., 5-gram)
B. Word2Vec
C. Unigram model
D. Bag of Words

41 What is the primary input to a neural network training a Word2Vec model?

A. Image pixels
B. One-hot encoded vectors of words
C. Audio signals
D. Parse trees

42 The term 'corpus' in NLP refers to:

A. A type of spelling error
B. A specific neural network layer
C. A body of text data
D. A computer algorithm

43 In edit distance, if we assign a higher cost to substitution than insertion/deletion, it implies:

A. The algorithm will fail
B. The distance will always be zero
C. Insertion is impossible
D. Typing a wrong letter is considered worse than missing a letter

44 What is the result of using a sliding window in N-gram generation?

A. It removes stop words
B. It converts text to uppercase
C. It calculates the edit distance
D. It creates a sequence of overlapping word chunks

45 Which of these words likely has a vector closest to 'frog' in a well-trained embedding space?

A. Philosophy
B. Galaxy
C. Toad
D. Steel

46 In an HMM, what connects hidden states to each other?

A. The Viterbi path
B. Transition probabilities
C. Emission probabilities
D. Observation vectors

47 What is 'Stupid Backoff' in the context of Language Models?

A. A way to delete wrong words
B. A smoothing method that uses lower-order N-grams if higher-order ones are missing
C. A type of neural network
D. A method to stop the algorithm

48 Which application primarily utilizes Probabilistic Language Models?

A. Speech Recognition
B. Image Compression
C. Network Routing
D. Database Management

49 In the context of Word Embeddings, what does 'Polysemy' refer to?

A. Words with multiple meanings
B. Words with similar spellings
C. Words that rhyme
D. Words in different languages

50 If P(A|B) is the probability of tag A following tag B, this is an example of:

A. Transition probability
B. Observation probability
C. Emission probability
D. Edit probability
Previous MCQ
Unit 2
Next MCQ
Unit 4