Sail E0 Webinar

MCQs

Total Questions : 20 | Page 2 of 2 pages
Question 11. Difficulties/Challenges in Word Sense Disambiguation (WSD)
  1.    to decide the sense of the word because different senses can be very closely related.
  2.    Completely different algorithm might be needed for different applications.
  3.    The problem of Inter-judge variance as the WSD systems are generally tested by having their results on a task compared against the task of human beings
  4.    Words can be easily divided into discrete sub-meanings.
 Discuss Question
Answer: Option D. -> Words can be easily divided into discrete sub-meanings.
Question 12. Which are common words usually removed in an NLP analysis?
  1.    Tokenization
  2.    Ngrams
  3.    Stopwords
  4.    Corpus
 Discuss Question
Answer: Option C. -> Stopwords
Question 13. Which is based on tagging and is statistically based as opposed to rule based?
  1.    NLTK
  2.    spaCy
 Discuss Question
Answer: Option B. -> spaCy
Question 14. Which are included in named entity recognition?
  1.    Time and dates
  2.    Nouns
  3.    Currency
  4.    All of above
 Discuss Question
Answer: Option D. -> All of above
Question 15. How do we get from NLP text analysis to stock price correlation?
  1.    Transform some NLP results into features.
  2.    Convert parts of speech to categorical variables
  3.    Recognize some named entities
  4.    VADER it
 Discuss Question
Answer: Option A. -> Transform some NLP results into features.
Question 16. Which is the main Python package we use for NLP?
  1.    Scikit-Learn
  2.    NLTK
  3.    NLP-LIB
  4.    PyNLP
 Discuss Question
Answer: Option B. -> NLTK
Question 17. What does spaCy tagging do?
  1.    Identifies more frequent words
  2.    Identifies importance and relevance
  3.    Identifies word order relationships
  4.    Identifies parts of speech
 Discuss Question
Answer: Option D. -> Identifies parts of speech
Question 18. Which is the process of turning different morphologies (i
  1.    Lemmatization
  2.    Tokenization
  3.    Ngrams
  4.    Stopwords
 Discuss Question
Answer: Option A. -> Lemmatization
Question 19. In a word cloud, what does the size correspond to?
  1.    Length
  2.    Frequency
  3.    Importance
  4.    Relation
 Discuss Question
Answer: Option B. -> Frequency
Question 20. Consider the following piece of codefromnltk
  1.    Calculates the similarity between the words ‘tree’ and ‘plant’.
  2.    You cannot find the similarity between two words without using WordNet.
  3.    A corpus is a large and structured set of machine-readable texts that have been produced in a natural communicative setting.
  4.    Word similarity is dependent on the context in which it is used
 Discuss Question
Answer: Option B. -> You cannot find the similarity between two words without using WordNet.

Latest Videos

Latest Test Papers