About NLP

Following are some of the multiple choice questions on the NLP with answers that will help the students in developing their knowledge.

NLP MCQ

1. Morphological Analysis

  • Does discourse analysis
  • Separate words into individual morphemes and identify the class of the morphemes
  • Is an extension of propositional logic
  • None of the above

2. Why we use named entity recognition in NLP?

  • Classify entities into predefined labels
  • Creating a set of vocabularies
  • Breaking sentences into words
  • None

3. What does NLP stand for? Write what the acronym means.

  • Natural Language Processing
  • Nationwide Loan Processing
  • Netware Lite Protocol
  • None of these

4. Consider the following piece of codefromnltk.corpus import wordnet as wn from nltk.corpus import wordnet_ic brown_ic = wordnet_ic.ic('ic-brown.dat') tree = wn.synsets("tree") plant = wn.synsets("plant")print(tree[0].lin_similarity(plant[0], brown_ic))Tick the statements which are true in this context.

  • Calculates the similarity between the words ‘tree’ and ‘plant’.
  • You cannot find the similarity between two words without using WordNet.
  • A corpus is a large and structured set of machine-readable texts that have been produced in a natural communicative setting.
  • Word similarity is dependent on the context in which it is used

5. In a word cloud, what does the size correspond to?

  • Length
  • Frequency
  • Importance
  • Relation

6. What are the names of lecturers in this NLP part?

  • Stefan Kosztolanyi
  • Sebastian Poliak
  • Martin Smira
  • Both A & B

7. Which of these are enghlish stopwords?

  • 'i', 'me', 'my', 'myself'
  • 'about', 'against', 'between', 'into'
  • 'happy', 'sad', 'angry', ' 'amazing'
  • Both A & B

8. Which are multiple word sequences?

  • Tokenization
  • Ngrams
  • Stopwords
  • Corpus

9. N-grams are defined as the combination of N keywords together. How many bi-grams can be generated from given sentence:“NPTEL videos are a great source to learn engineering courses”

  • 7
  • 8
  • 9
  • 10

10. Which of the following sense for the word “language” is not available in wordnet? i. a systematic means of communicating by the use of sounds or conventional symbol ii. communication by word of mouth iii. the cognitive processes involved in producing and understanding linguistic communication iv. the style of a piece of writing or speech v. the mental faculty or power of vocal communication

  • 3
  • 5
  • 4
  • None of these

11. What is the field of Natural Language Processing (NLP)?

  • Computer Science
  • Artificial Intelligence
  • Linguistics
  • All of the mentioned

12. ____________ is a Python library to make programs that work with natural language.

  • NLTK
  • Pandas
  • Seaborn
  • BeautifulSoup

13. Tick whichever is an application Named Entity Recognition (NER)

  • Classifying content for NEWS providers
  • Efficient Search Algorithms
  • Analysis the rude behavior from customer feedback
  • All of above

14. Which are common words usually removed in an NLP analysis?

  • Tokenization
  • Ngrams
  • Stopwords
  • Corpus

15. Difficulties/Challenges in Word Sense Disambiguation (WSD) .Tick which is (FALSE) from the statements given below

  • to decide the sense of the word because different senses can be very closely related.
  • Completely different algorithm might be needed for different applications.
  • 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
  • Words can be easily divided into discrete sub-meanings.

16. Which is based on tagging and is statistically based as opposed to rule based?

  • NLTK
  • spaCy

17. How do we get from NLP text analysis to stock price correlation?

  • Transform some NLP results into features.
  • Convert parts of speech to categorical variables
  • Recognize some named entities
  • VADER it

18. Which are included in named entity recognition?

  • Time and dates
  • Nouns
  • Currency
  • All of above

19. What does spaCy tagging do?

  • Identifies more frequent words
  • Identifies importance and relevance
  • Identifies word order relationships
  • Identifies parts of speech

20. Which is the main Python package we use for NLP?

  • Scikit-Learn
  • NLTK
  • NLP-LIB
  • PyNLP

21. Which is the process of turning different morphologies (i.e. versions) of a word into its base form?

  • Lemmatization
  • Tokenization
  • Ngrams
  • Stopwords

22. Which is a collection of documents?

  • Tokenization
  • Ngrams
  • Stopwords
  • Corpus

23. Which function would you use to implement a bag of words by creating a matrix of token counts?

  • CountVectorizer()
  • fit_tranform()
  • get_feature_names()
  • download()

24. If speed is focused, then _______ should be used since ________ scans a WordNet corpus and a corpus for stop words as well as requires you to define a parts-of-speech to produce root forms of words which consumes time and processing. If you are building a language application in which language is important, you should use _______ as it uses a corpus to match root forms.

  • stemming, lemmatization, lemmatization
  • lemmatization, stemming, stemming

25. NLP is concerned with the interactions between computers and human (natural) languages.

  • True
  • False

26. Given a stream of text, Named Entity Recognition determines which pronoun maps to which noun.

  • False
  • True

27. Consider the sentence: “The touch screen was cool; however, the voice quality and battery were very poor”. Which of the following are true?

  • Aspect: “touch screen”, Sentiment: Positive, Opinion Phrase: “cool”.
  • Aspect: “voice quality”, Sentiment: Negative, Opinion Phrase: “very poor”.
  • Aspect: “battery”, Sentiment: Negative, Opinion Phrase: “very poor”.
  • All of above

28. Which of the following Affective States does Sentiment Analysis mostly focus on?

  • Mood
  • Personality Traits
  • Attitudes
  • Emotion

29. While working with context extraction from a text data, you encountered two different sentences: The tank is full of soldiers. The tank is full of nitrogen. Which of the following measures can be used to remove the problem of word sense disambiguation in the sentences?

  • Compare the dictionary definition of an ambiguous word with the terms contained in its neighborhood
  • Co-reference resolution in which one resolute the meaning of ambiguous word with the proper noun present in the previous sentence
  • Use dependency parsing of sentence to understand the meanings
  • None of these

30. What are the possible features of a text corpusCount of word in a document Boolean feature – presence of word in a document.Vector notation of word Part of Speech Tag Basic Dependency Grammar Entire document as a feature

  • 12
  • 123
  • 1234
  • 12345

31. Which of the following regular expression can be used to identify date(s) present in the text object?“The next meetup on data science willbe held on 2017-09-21, previously it happened on 31/03, 2016”

  • \d{4}-\d{2}-\d{2}
  • (19|20)\d{2}-(0[1-9]|1[0-2])-[0-2][1-9]
  • (19|20)\d{2}-(0[1-9]|1[0-2])-([0-2][1-9]|3[0-1])
  • None of the above

32. Tick what is true about WordNet from the following sentences

  • A hierarchically organized lexical database
  • A machine-readable thesaurus, and aspects of a dictionary
  • Is a lexical database of semantic relations between words
  • All of above

33. Consider the following given sentences. Match the lexical relations between the first word (w​1​) to the second word (w​2​) i.e. w​1​ is a <lexical relation> of w​2. · Invention of the wheel​ is one of the landmarks in the history of mankind.· Companies are trying to make driverless car.· Golden daffodils​ are fluttering and dancing in the breeze.· Mumbai has unique flower ​park.1. Holonym i.wheel-car 2. Hyponym ii.car-wheel 3. Meryonym iii.daffodils-flower 4. Hypernym iv. flower- daffodils

  • 1-iii, 2-ii, 3-iv, 4-i
  • 1-ii, 2-iii, 3-i, 4-iv
  • 1-ii, 2-iii, 3-iv, 4-i
  • 1-i, 2-ii, 3-iii, 4-iv

34. Morphotacticsis a model of

  • Spelling modifications that may occur during affixation
  • How and which morphemes can be affixed to a stem
  • All affixes in the English language
  • N-grams of affixes and stems

35. A vader compound score of 1.02 evaluates to

  • positive sentiment
  • neutral sentiment
  • negative sentiment
  • none of the above

36. From the sentence “Fintech Online Course”, how many bigrams can be created?

  • 1
  • 2
  • 3
  • 4

37. Between NLTK and spaCy, which is based on tagging and is statistically based as opposed to rule based?

  • NLTK
  • spaCy

38. Between NLTK and spaCy, which is faster and better for larger datasets?

  • NLTK
  • spaCy

39. What were the objectives of NLP day 1?

  • Tokenizing texts into sentences and words
  • Implementing ngrams and word clouds
  • Implement lemmatization and stopwording
  • All of above

40. Which step is the process of breaking down documents into smaller units of analysis?

  • Tokenization
  • Ngrams
  • Stopwords
  • Corpus

41. Which function would you use to retrieve the list of unique words?

  • CountVectorizer()
  • fit_tranform()
  • get_feature_names()
  • download()

42. Which is a model of measuring the incidence of known words?

  • A high weight in TF-IDF
  • A low weight in TF-IDF
  • A bag of words
  • A corpus

43. Which is a high term frequency and low document frequency?

  • A high weight in TF-IDF
  • A low weight in TF-IDF
  • A bag of words
  • A corpus

44. Which news sources did we use?

  • News API
  • Reuters
  • Bloomberg
  • Both A & B

45. Which is the most useful metric from VADER for sentiment analysis?

  • Positivity
  • Compound
  • Negative
  • Intensity

46. Which company's tone analyzer service did we discuss?

  • Amazon
  • Apple
  • Google
  • IBM

47. What were the objectives of NLP day 2?

  • Analyze sentiments and tone from news feeds.
  • Use NLTK and VADER to classify news as positive, negative, or neutral.
  • Perform data preparation techniques for sentiment analysis.
  • All of above

48. Which are python libraries used in NLP?

  • spacy
  • pandas
  • nltk
  • All of above

49. What kind of charts are used in visualisations of results?

  • Barchart
  • Scatterplot
  • Windowplot
  • Both A & B

50. The Bag-of-Words approach:

  • keeps word order, disregards word multiplicity
  • keeps word order, keeps word multiplicity
  • disregards word order, keeps word multiplicity
  • disregards word order, disregards word multiplicity

Enjoyed the Quiz. Share this with friends

Comments

Add Your Review

Your email address will not be published.

Subscribe to Newsletter!

Subscribe to get latest updates and information.