Natural Language Processing MCQ



Question 151 : A web page whose content doesn't vary from one request to another is called a:

  1. Text Page
  2. Dynamic Page
  3. Active Server Page
  4. Static Page
  

Question 152 : Which of the following is an advantage of normalizing a word?

  1. It guarantees word to be inconsistent
  2. It helps in reducing the randomness in the word
  3. It increases the false negatives
  4. It increases the dimensionality of the input
  

Question 153 : Closed classes of POS are those with relatively fixed membership

  1. Yes
  2. No
  3. Cannot Say
  4. May be yes
  

Question 154 : Stop words are-

  1. words that frequently found in a document
  2. long sound words
  3. words that are not important for text wrapping
  4. Creating a set repeting words
  

Question 155 : Elements of Semantic analysis

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

Question 156 : 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 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. 1-iii, 2-ii, 3-iv, 4-i
  2. 1-ii, 2-iii, 3-i, 4-iv
  3. 1-ii, 2-iii, 3-iv, 4-i
  4. 1-i, 2-ii, 3-iii, 4-iv
  

Question 157 : What is Deixis

  1. A word that is quite hard to spell
  2. Words that are context bound where meaning depends on who is being referred to, where something is happening or when something is happening.
  3. An implied meaning that has to be inferred as a result of a conversational maxim being broken
  4. A word that is quite easy to spell
  

Question 158 : 1."The Tank Was Full Of Water.". "I Saw The Military Tank".Here Tank Is Used In Different Context, Which Type Of Ambiguity Is This?

  1. Semantic Ambiguity
  2. Syntactic Ambiguity
  3. Anaphoric Ambiguity
  4. Syntactical Ambiguity
  

Question 159 : HMM model formula is combination of

  1. N gram and Naive bayes
  2. Logistic regression
  3. SVM
  4. Euclidean distance between words
  

Question 160 : ___________technique looks at the meaning of the word.

  1. Stemming
  2. Lemmatization
  3. Stop word identification
  4. Morphological Analysis
  

Question 161 : " I appoint you chairman of the committee" is which type of speech act?

  1. Commissives
  2. Directives
  3. Declarations
  4. Representatives
  

Question 162 : Software designed for taking i/p data(text) and give structural representation of the input after checking the correct syntax or grammar is

  1. Compiler
  2. Parser
  3. Painter
  4. Easydraw
  

Question 163 : Which of the following is a example of irregular noun form?

  1. Fox
  2. Dog
  3. Mouse
  4. Cat
  

Question 164 : Function morphemes are also called ______

  1. open-class morphemes
  2. sub-class morphemes
  3. super-class morphemes
  4. closed-class morphemes
  

Question 165 : Which statement is true

  1. Rule based methods are language independent
  2. Stochastic methods are language independent
  3. It is highly complex task to resolve ambiguities especially at lower levels of NLP
  4. Disambiguation task are is more challenging in Resourceful language as compared to Resourceless language
  

Question 166 : For HMM Model, with N hidden states, V observable states, what is the dimension of State Transition Probability Matrix

  1. N×V
  2. N×1
  3. N×N
  4. 1For HMM Model, with N hidden states, V observable states, what is the dimension of Emission Probability ×N
  

Question 167 : When a referent is first mentioned in a discourse, we say that a representation for it is __________ into the model.

  1. created
  2. evoked
  3. accessed
  4. initiated
  

Question 168 : Which one of the following is not a pre-processing technique in NLP

  1. Stemming and Lemmatization
  2. Sentiment analysis
  3. Removal of stop words
  4. Converting to lowercase
  

Question 169 : Mini-Corpus given, I am Sam Sam I am I do not like green eggs and ham What will be bigram probability of P(am | I)?

  1. 0.67
  2. 0.33
  3. 0.5
  4. 0.25
  

Question 170 : 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 171 : Dog is hyponym of

  1. Forest
  2. Human
  3. Animal
  4. Automobile
  

Question 172 : 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 173 : Which application use to determine people in context?

  1. Stemming
  2. Lemmatization
  3. Stop word removal
  4. Named entity recognition
  

Question 174 : The original Brown tagset uses two of the most commonly used tagsets are__________ & _____________.

  1. 50-tag Penn Treebank tagset, the medium-sized 70 tag C5 tagset
  2. Medium 10-tag Penn Treebank tagset, the medium-sized 21 tag C5 tagset
  3. Small 45-tag Penn Treebank tagset, the medium-sized 61 tag C5 tagset
  4. Medium 87-tag Penn Treebank tagset, the 45 medium-sized 21 tag C5 tagset
  

Question 175 : Tf-Idf Helps You To Establish?

  1. Most Frequently Occurring Word In The Document
  2. Most Important Word In The Document
  3. Most Important Sentence In The Document
  4. Most Frequently Occurring Sentence In The Document
  

Question 176 : Which of the following techniques is most appropriate to the process of word normalization

  1. Stemming
  2. Lemmatization
  3. Stop word removal
  4. Rooting
  

Question 177 : To evaluate the effectiveness of an IR system the output from a standard query executed against the test IR system is compared with the known output from a:

  1. internet collection
  2. reference book
  3. separate IR system.
  4. standard test collection
  

Question 178 : Get (to take) - get (to become), is example of ______

  1. Synonym
  2. Hyponym
  3. Homonym
  4. Polysemy
  

Question 179 : Identify the artificial language

  1. Java
  2. Maori
  3. Kazakh
  4. Zulu
  

Question 180 : ..............ambiguity refers to a situation where the context of a phrase gives it multiple interpretation

  1. Pragmatic
  2. Anaphoric
  3. Discourse
  4. Cataphoric
  

Question 181 : Morphological Segmentation _______________

  1. Does Discourse Analysis
  2. Separate words into individual morphemes and identify the class of the morphemes
  3. Is an extension of propositional logic
  4. Is an extension of propositional limit
  

Question 182 : The statement “ eat a pizza” can be represented as

  1. NP → Verb VP
  2. VP → Verb PP
  3. VP → Verb NP
  4. VP → Verb NP PP
  

Question 183 : e.g. 'do', 'eat', 'go' are examples of which type of verb

  1. Regular verb
  2. Irregular verb
  3. Complex verb
  4. Normal verb
  

Question 184 : What Can Be Called As "The Knowledge Of What Has Been Said Earlier"

  1. Situational Context
  2. Background Knowledge
  3. Co-Textual Context
  4. Operational Knowledge
  

Question 185 : Which of the following is not true input for the NLP?

  1. Image
  2. Text
  3. Types input
  4. Speech
  

Question 186 : Which Of The Following Is An Nlp Task That Involves Determining All Referring Expressions That Point To The Same Real-World Entity?

  1. Coreference Resolution
  2. Named Entity Recognition
  3. Information Extraction
  4. Stop Word
  

Question 187 : Clock = digital - analog - alarm

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

Question 188 : How many bi-grams can be generated from given sentence:- "This is NLP book."?

  1. 3
  2. 2
  3. 4
  4. 1
  

Question 189 : ________________ extracts all the documents containing the key words

  1. Information Extraction
  2. Information Retrieval
  3. Inflection
  4. Inflation
  

Question 190 : NLP Stands for.

  1. Natural Language Protocol
  2. Natural Lingual Protocol
  3. Natural Lingual Processing
  4. Natural Language Processing
  

Question 191 : Two words are there with different spelling but sound is same wring(1) and wring(2). First one means to twist something and second one means you wear in your finger. This is an example of

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

Question 192 : Mango is hyponym of

  1. Forest
  2. Human
  3. Fruits
  4. Sweet
  

Question 193 : Which of the following component of NLP?

  1. Pragmatic analysis
  2. Entity extraction
  3. Syntactic analysis
  4. Pragmatic analysis & Entity extraction & Syntactic analysis
  

Question 194 : Token and morpheme are always same.

  1. Yes
  2. NO
  3. Probability based
  4. Randomization based
  

Question 195 : Where the additional variables does are added in HMM?

  1. a)Temporal model
  2. b)Reality model
  3. c)Probability model
  4. d)In all three models, temporal, reality and probability model
  

Question 196 : ___: How we put words together,___ : word meanings, ___ : speaker meaning

  1. Syntax,semantics,pragmatics
  2. Semantics,syntax,pragmatics
  3. Semantics,syntax,pragmatics
  4. Social; academic, semantic
  

Question 197 : Inferrables, discontinuos sets and ______ are the three types of referents that complicate the reference resolution problem.

  1. Indefinite Noun phrases
  2. demonstratives
  3. one anaphora
  4. generics
  

Question 198 : 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 199 : Corpus-Based Approaches Use Either Supervised Or Unsupervised Learning. Supervised Methods Require ___________ Whereas Unsupervised Methods Eliminate The Need Of Tagged Data But Usually Perform Only _________________.

  1. Tagged Data, Word Sense Discrimination
  2. Untagged Data, Word Sense Discrimination
  3. Untagged Data, Word Commonsense Discrimination
  4. Untagged Data, Word Sense Indiscrimination
  

Question 200 : In the English language inflectional morphemes can be...

  1. Prefixes, Suffixes and Infixes
  2. Suffixes only
  3. Infixes Only
  4. Prefixes, Suffixes and Infixes