Natural Language Processing (NLP) MCQ's




Question 121 :
Where the additional variables does are added in HMM?

  1. Temporal model
  2. Reality model
  3. Probability model
  4. In all three models, temporal, reality and probability model
  

Question 122 :
HMM graphs consist of a Hidden Space and Observed Space, where the hidden space consists of the _______ and the observed space is the ______

  1. Input, Categories
  2. Values, Variables
  3. Labels, Input
  4. Variables, Values
  

Question 123 :
Google Translate is one of the ________________ application.

  1. Machine translation
  2. Information Retrieval
  3. Information Extraction
  4. Summarisation
  

Question 124 :
How many different lexemes are there in the following list?man, men, girls, girl, mouse

  1. 1
  2. 2
  3. 3
  4. 4
  

Question 125 :
A set of words that denotes a subcategory of a more general class

  1. Hyponymy
  2. Meronymy
  3. Polysemy
  4. Clines
  

Question 126 :
_____________ is the process of understanding if a given text is talking positively or negatively about a given subject (e.g. for brand monitoring purposes).

  1. Syntactical analysis
  2. Hybrid analysis
  3. Sentiment Analysis
  4. Lexical analysis
  

Question 127 :
In test summarisation an ___________ is formed by selecting phrases or sentences from the document to be summarized

  1. Abstract
  2. Extract
  3. Information
  4. Prose
  

Question 128 :
Which of the following is efficient representation of text data?

  1. Bag of Word
  2. TF-IDF
  3. Word Vector
  4. BERT
  

Question 129 :
In 1969 Roger schank introduced ________________ dependency theory for NL understanding

  1. Conceptual
  2. Bilateral
  3. Trilateral
  4. Textual
  

Question 130 :
Ir System : Subset Of Documents : : ? : Subset Of Information Within Document

  1. Speech Recognition
  2. Natural Language Interfaces To Db
  3. Information Extraction
  4. Information Retrieval
  

Question 131 :
In NLP, The process of removing words like 'and', 'is', 'a', 'an', 'the' from a sentence is called as

  1. Stemming
  2. Lemmatization
  3. Stop word
  4. derivation
  

Question 132 :
To find relevance of word in a document technique used

  1. TF-IDF
  2. Lemma
  3. Tokenizer
  4. Pos tagging
  

Question 133 :
From a verb to a specific manner elaboration of that web

  1. Homonymy
  2. Troponym
  3. Polysemy
  4. Metonymy
  

Question 134 :
Which of the following grammars generates strings with any number of 1’s?

  1. S __> 1A, A __> ε
  2. S __>1S, S__> ε
  3. S __>S1, S__> ε
  4. S __>1SA, S__> ε
  

Question 135 :
Syntactic analysis or parsing may be defined as the process of ________ the _______ of symbols in Natural language conforming to the rules of formal grammar.

  1. Analyzing - Strings
  2. Defining - Groups
  3. Reducing - Arrays
  4. Reviewing - Letters
  

Question 136 :
Identifying intentions in dialogue is ________

  1. Morphology
  2. Semantics
  3. Pragmatics
  4. Discourse
  

Question 137 :
Pronouns usually refer to entities that were introduced no further than one or two sentences back in the ongoing discourse, whereas ________________ can often refer further back.

  1. demonstratives
  2. indefinite noun phrase
  3. one anaphora
  4. definite noun phrases
  

Question 138 :
To identify the category of each word in a sentence

  1. Parsing
  2. POS
  3. Semantic Analysis
  4. Pragmatics
  

Question 139 :
Subsequent reference to an already introduced entity; referring back (__>Paul's on the phone. I don't wanna talk to __>him.)

  1. Face
  2. Words
  3. Anaphora
  4. Cataphora
  

Question 140 :
In NLP, The algorithm decreases the weight for commonly used words and increases the weight for words that are not used very much in a collection of documents

  1. Term Frequency (TF)
  2. Inverse Document Frequency (IDF)
  3. Word2Vec
  4. Latent Dirichlet Allocation (LDA)
  

Question 141 :
Which one of the following is morpheme of the word 'unbelievable'?

  1. un
  2. unbe
  3. evable
  4. able
  

Question 142 :
Which method of sentiment analysis uses a variety of words annotated by polarity score, to decide the general assessment score of a given content.

  1. Word-Based
  2. Lexicon-Based
  3. Hybrid
  4. Opinion-Based
  

Question 143 :
Inflectional morphology have the scope of__________________

  1. unlimited applicability
  2. possibly literal
  3. no communicability
  4. more base allomorph
  

Question 144 :
Elements of Semantic analysis

  1. Hyponymy
  2. Homonymy
  3. Polysemy
  4. Hyponymy, Homonymy, Polysemy
  

Question 145 :
Consider the following corpus of 3 sentences. 1) I am here 2) who am I. 3) I would like to go. Calculate​ P(here|am) ​assuming a bi-gram language model.

  1. 43864
  2. 1
  3. 43832
  4. 43833
  

Question 146 :
In Sentiment analysis

  1. List the topics that a document deals with
  2. Assess the emotional content of a document
  3. Compress a document as much as possible without losing meaning, producing another document
  4. Given a question in natural language, provide an appropriate answer in natural language
  

Question 147 :
The Context Of A Word Provides Useful Information About Word Sense. Which Algorithms Can Be Braodly Classified Into Knowledge-Based And Corpus-Based Approaches

  1. Context-Based Disambiguation
  2. Context-Free Grammar
  3. Regular Expressions
  4. Context-Based Ambiguation
  

Question 148 :
Google Translate is one of the ________________ application.

  1. Machine translation
  2. Information Retrieval
  3. Information Extraction
  4. Information Generation
  

Question 149 :
Parts-of-Speech tagging determines ___________

  1. part-of-speech for each symbol only generated dynamically as per meaning of the sentence
  2. part-of-speech for each word dynamically as per sentence structure
  3. all stem for a specific word given as input
  4. all lema for a specific word given as input
  

Question 150 :
When did first patent's for transating machine were applied for

  1. In the mid of 1930
  2. at the end of 1930
  3. In the begining of 1930
  4. In the mid of 1931
  
Pages