MauryaHub PYQ Practice

da5005_2024T3_Q1_NA.pdf

Introduction to Natural Language Processing (i-NLP) · Quiz 1 · Sep 2024

← Course papers · Start practice / exam

Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.

Question 221 MCQ · 3.0 marks

In a whimsical language where adjectives change based on the weather, an FST is designed to transform “happy” into “happyrain” on rainy days and “happysun” on sunny days. If the FST has 5 states for “happy” and 3 states each for weather conditions, what’s the minimum total number of states required?
  1. 8
  2. 11
  3. 13
  4. 15

A published solution is not available for this question yet.

Question 222 MCQ · 3.0 marks

[[IMAGE:febf6125e7ab8bec_3_0]]
Source diagram or notation
  1. “unlearned”
  2. “undefined”
  3. “unfinished”
  4. All of these

A published solution is not available for this question yet.

Question 223 MCQ · 3.0 marks

[[IMAGE:febf6125e7ab8bec_4_1]]
Source diagram or notation
  1. The string is rejected.
  2. The string is accepted.
  3. The FSA transitions to an error state.
  4. The output is “11”.

A published solution is not available for this question yet.

Question 224 MCQ · 3.0 marks

In a graph-based dependency parser using edge-factored scoring, the following edge scores have been calculated for a sentence: [[IMAGE:febf6125e7ab8bec_4_2]] What is the score of the maximum spanning tree (assuming all other possible edges have lower scores)?
Source diagram or notation
  1. 1.5
  2. 1.6
  3. 1.7
  4. 1.8

A published solution is not available for this question yet.

Question 225 MCQ · 3.0 marks

In evaluating a dependency parser, the following results were obtained on a test set of 500 words: • 450 words have the correct head • 425 words have both the correct head and correct label • 475 words have the correct label What are the Unlabeled Attachment Score (UAS) and Label Accuracy Score (LS)?
  1. UAS: 90%, LS: 85%
  2. UAS: 90%, LS: 95%
  3. UAS: 85%, LS: 95%
  4. UAS: 85%, LS: 90%

A published solution is not available for this question yet.

Question 226 MCQ · 2.0 marks

A legal document analysis tool is being developed to identify key clauses. If the tool correctly identifies 80 relevant clauses out of 100 actual relevant clauses, and incorrectly flags 20 irrelevant clauses as relevant, what is the F1 score of the tool?
  1. 0.80
  2. 0.82
  3. 0.85
  4. 0.89

A published solution is not available for this question yet.

Question 227 MCQ · 2.0 marks

In the sentence “The old Shakespearean Globe Theatre on the banks of the Thames hosted a modern rendition of ’A Midsummer Night’s Dream’”, which phrase is NOT a Named Entity?
  1. Shakespearean
  2. Globe Theatre
  3. Thames
  4. A Midsummer Night’s Dream

A published solution is not available for this question yet.

Question 228 MCQ · 1.0 marks

In processing the sentence “After John beat him in chess, Bill lost his Queen,” which NLP level is most crucial for understanding “Queen” ?
  1. Lexical
  2. Semantic
  3. Discourse
  4. Pragmatic

A published solution is not available for this question yet.

Question 229 MCQ · 1.0 marks

Anaphora resolution, which falls under the discourse level of NLP, can be fully solved using only syntactic parsing techniques.
  1. Yes
  2. No

A published solution is not available for this question yet.

Question 230 MCQ · 1.0 marks

In the sentence “I saw her duck,” morphological analysis alone is sufficient to determine whether “duck” is being used as a noun or a verb.
  1. Yes
  2. No

A published solution is not available for this question yet.

Question 231 MCQ · 1.0 marks

What is a primary feature of agglutinative languages?
  1. Morphemes are fused together, making them inseparable.
  2. Morphemes are added like beads on a string, each representing one grammatical feature.
  3. Each word consists of a single morpheme.
  4. Morphology does not exist in these languages.

A published solution is not available for this question yet.

Question 232 MCQ · 1.0 marks

In morphological analysis, what is the primary difference between Item and Arrangement (IA) and Item and Process (IP) approaches?
  1. IA focuses on concatenation, while IP uses rules and allomorphs.
  2. IA is used for synthetic languages, while IP is for analytic languages.
  3. IA is word-based, while IP is morpheme-based.
  4. IA uses paradigms, while IP uses linear sequencing.

A published solution is not available for this question yet.

Question 233 MCQ · 1.0 marks

Context-Free Grammar (CFG) rules can only generate sentences with a fixed word order.
  1. Yes
  2. No

A published solution is not available for this question yet.

Question 234 MCQ · 1.0 marks

The CKY parsing algorithm requires the grammar to be in Chomsky Normal Form (CNF).
  1. Yes
  2. No

A published solution is not available for this question yet.

Question 235 MCQ · 1.0 marks

Treebanks are automatically generated without human intervention.
  1. Yes
  2. No

A published solution is not available for this question yet.

Question 236 MCQ · 1.0 marks

In the sentence “He gave her a book,” the dependency relationship between “gave” and “book” is labeled as nsubj.
  1. Yes
  2. No

A published solution is not available for this question yet.

Question 237 MCQ · 1.0 marks

In the sentence “The cat sat on the mat,” the prepositional phrase “on the mat” serves as a dependent of “sat” in a case relation.
  1. Yes
  2. No

A published solution is not available for this question yet.

Question 238 MSQ · 2.0 marks

Which of the following NLP tasks would benefit from processing at the discourse level?
  1. Generating a coherent multi-paragraph story
  2. Summarizing a long document
  3. Resolving pronouns in a conversation
  4. Determining the sentiment of a single word
  5. Identifying the topic shifts

A published solution is not available for this question yet.

Question 239 MSQ · 2.0 marks

Which of the following are characteristics of Naive Bayes classifiers? (Select all that apply)
  1. Assumes independence between features
  2. Often used for POS tagging and NER
  3. Requires a large amount of training data
  4. Provides probabilistic outputs
  5. Cannot handle multi-class classification

A published solution is not available for this question yet.

Question 240 MSQ · 2.0 marks

Which of the following are applications of clustering in NLP tasks? (Select all that apply)
  1. Grouping similar entities in NER
  2. Unsupervised POS tagging
  3. Sentiment analysis
  4. Word clustering into syntactic categories
  5. Machine translation

A published solution is not available for this question yet.

Question 241 MSQ · 1.0 marks

In developing a sarcasm detection system for social media posts, which levels of NLP processing would be most crucial?
  1. Phonological
  2. Semantic
  3. Discourse
  4. Pragmatic
  5. Syntactic

A published solution is not available for this question yet.

Question 242 NAT · 3.0 marks

In a Hidden Markov Model (HMM) for POS tagging, the transition probability from the tag NOUN (noun) to VERB (verb) is 0.3, and the transition probability from VERB (verb) to DET (determiner) is 0.4. What is the joint transition probability of the sequence NOUN → VERB → DET?

    A published solution is not available for this question yet.

    Question 243 NAT · 3.0 marks

    In a Conditional Random Field (CRF) model for POS tagging, if there are 6 features per word and the sentence has 10 words, how many total feature values does the model compute for this sentence?

      A published solution is not available for this question yet.

      Question 244 NAT · 3.0 marks

      In a POS tagging model, out of 500 total predictions made, 420 were correct. What is the accuracy of the model as a percentage (rounded to two decimal places)?

        A published solution is not available for this question yet.

        Question 245 NAT · 3.0 marks

        In a binary classification task, the number of True Positives (TP) is 80, and the number of False Positives (FP) is 20. What is the precision of the model as a decimal (rounded to two decimal places)?

          A published solution is not available for this question yet.

          Question 246 NAT · 2.0 marks

          In a semantic role labeling evaluation, a model has identified 100 correct semantic roles out of 120 total semantic roles it predicted. What is the precision of the model as a decimal (rounded to two decimal places)?

            A published solution is not available for this question yet.