Font size
WorksheetsNLP Multiple Choice Questions (Part 1)
Total questions: 150
Worksheet time: 1hrs 15mins
What is the primary purpose of Natural Language Processing (NLP)?
To enable computers to understand, analyze, and process human languages.
To generate binary code for machine execution.
To analyze the grammar of computer programming languages.
To convert numerical data into visual representations.
Which of the following is NOT a feature of natural languages?
They are static and do not change over time.
They are redundant.
Governed by rules like syntax and lexicon.
Information can be conveyed in multiple ways.
Which NLP application is used to generate captions for video content in real-time?
Language Translation
Sentiment Analysis
Text Classification
Autogenerated Captions
Which stage of NLP is responsible for checking the grammar and structural correctness of sentences?
Pragmatic Analysis
Syntactic Analysis
Lexical Analysis
Semantic Analysis
What is the main task of Semantic Analysis in NLP?
Analyzing the relationship between successive sentences.
Assessing the meaningfulness of the input text.
Checking the grammar of the sentences.
Dividing text into sentences and words.
The term "pulling your leg" is a good example for which stage of NLP?
Syntactic Analysis
Pragmatic Analysis
Lexical Analysis
Semantic Analysis
What is a "corpus" in the context of text processing?
A single document.
A special character in a sentence.
A collection of written text from multiple documents.
A word that has been stemmed.
The process of dividing sentences into words, numbers, and special characters is called:
Segmentation
Tokenization
Normalization
Stemming
Which of the following is a key characteristic of "stop words"?
They are frequently occurring words that do not add significant value.
They are always meaningful and essential for context.
They have the lowest occurrence in the text.
They add the most value to the corpus.
What is the difference between stemming and lemmatization?
Stemming is slower than lemmatization.
Stemming produces a meaningful root word, while lemmatization does not.
Stemming removes affixes, and the resulting word may not be meaningful, while lemmatization ensures the root word is meaningful.
They are the same process with different names.
In the Bag of Words model, what does the "bag" symbolize?
That the unique words are stored in a bag-like structure.
That the sequence of sentences is preserved.
That only the most important words are kept.
That the sequence of words or tokens does not matter.
What does TFIDF stand for?
Term Frequency-Inverse Document Frequency
Term Frequency-Integrated Document Function
Text Feature-Inverse Document Frequency
Total Frequency-In-Document Function
Which of the following is a TFIDF application?
Document Classification
Chatbot Development
Image Recognition
Voice Synthesis
Which of the following tools is a "no-code" NLP tool mentioned in the document?
Python
NLTK
SpaCy
MonkeyLearn
What is a chatbot?
A program that generates random sentences.
A computer program that simulates human conversation.
A tool used to extract keywords from text.
A type of database for storing textual data.
Which of the following is a primary function of a chatbot in an e-commerce site?
To perform mathematical calculations.
To generate sales leads and increase sales.
To translate the website into different languages.
To write code for the website.
The conversion of a word like "healed" to its base form "heal" is an example of which text processing technique?
Tokenization
Lemmatization or Stemming
What is the key concept illustrated by the sentence "His face turned red after he found out that he took the wrong bag"?
The importance of grammar.
The process of stemming.
The significance of context in understanding meaning.
The need for tokenization.
Which tool is a Python library for text processing?
MonkeyLearn
NLTK
Cleverbot
Orange Data Mining
In the TFIDF calculation, what does a low Inverse Document Frequency (IDF) value indicate for a word?
The word is rare and valuable.
The word is a stop word and has a negligible value.
The word is essential for document classification.
The word has a high term frequency in one document.
What is the core idea of a Bag of Words model?
Representing text as a collection of words, disregarding their order.
Preserving the grammatical structure of sentences.
Counting the number of unique words in a document.
Creating a document vector for each document.
What does the term "lexicon" refer to in the context of NLP?
A set of grammatical rules.
The output of the semantic analysis stage.
The process of dividing text into paragraphs.
A collection of various words and phrases used in a language.
Which step of text normalization ensures that "Hello," "hello," and "HELLO" are treated as the same word?
Converting text to a common case
Tokenization
Stop word removal
Stemming
What is the relationship between Discourse Integration and preceding/succeeding sentences?
It removes unnecessary words from them.
It forms a relationship between them to create a coherent story.
It segments them.
It converts them to a common case.
According to the document, what is the primary challenge for computers in understanding human language?
Human languages are too simple.
Human languages are complex and require simplification.
Computers can only process visual data.
Computers lack the necessary programs.
A word with a high TFIDF value is likely to have:
Low term frequency and high document frequency.
High term frequency and high document frequency.
Low term frequency and low document frequency.
High term frequency and low document frequency.
What is the process of normalizing text to a lower level called?
Text Summarization
Text Normalization
Text Categorization
Text Simplification
A document vector is created in which step of the Bag of Words algorithm?
TFIDF calculation
Creating document vectors
Creating a Dictionary
Text Processing
What is the primary function of keyword extraction?
To translate a text into different languages.
To classify a document into a category.
To automatically identify and extract the most important words or phrases from a text.
To check the grammatical structure of a sentence.
What is the main goal of text normalization?
To make text visually appealing.
To prepare textual data for machine learning.
To translate text to another language.
To make text more complex.
Which NLP stage focuses on the practical and logical relevance of a sentence in the real world?
Semantic Analysis
Lexical Analysis
Syntactic Analysis
Pragmatic Analysis
What is the first step in the Natural Language Processing (NLP) process?
Syntactic Analysis
Semantic Analysis
Lexical Analysis
Pragmatic Analysis
Which of the following is a benefit of using a chatbot on an e-commerce site?
It can only handle simple, scripted conversations.
It can analyze visual data.
It can process numerical data.
It can generate sales leads.
What is the main idea behind a "Bag of Words" model?
It only works for very short sentences.
It counts the frequency of words while ignoring their sequence.
It is a model for translating languages.
It focuses on the grammatical relationships between words.
What is the main purpose of the Inverse Document Frequency (IDF) component in TFIDF?
To measure the frequency of a word in a single document.
To reduce words to their root form.
To classify documents into categories.
To assess the importance of a word by penalizing words that appear frequently across many documents.
Which of the following statements about TFIDF is correct?
The TFIDF value is not related to TF or DF.
Words with low TF and high DF have a high TFIDF value.
Words with high TF and high DF have a high TFIDF value.
Words with high TF and low DF have a high TFIDF value.
What is a "lemma" in the context of lemmatization?
A word that is a stop word.
A word with no meaning.
A word that has not been normalized.
A meaningful word that is the root of another word.
What is the primary difference between a "script-bot" and a "smart-bot"?
There is no difference; the terms are interchangeable.
Script-bots have a limited, pre-defined set of responses, while smart-bots can learn and interact more dynamically.
Script-bots are used for sales, while smart-bots are for customer service.
Script-bots are AI-powered, while smart-bots are not.
What is the main advantage of lemmatization over stemming?
It is better for identifying stop words.
It always produces meaningful words.
It is less complex.
It is faster.
What is the process of breaking a large body of text into structural paragraphs, sentences, and words?
Discourse Integration
Lexical Analysis
Syntactic Analysis
Pragmatic Analysis
The TFIDF value of a word like "and" or "the" in a large corpus is typically:
High
Low or zero
Highly variable
Dependent on its grammatical role
In the context of NLP, what does "Discourse Integration" refer to?
The process of converting text to lowercase.
The process of checking the grammar.
The process of forming a coherent story between sentences.
The process of breaking down words into their root forms.
Which of the following is an example of a "No-Code" NLP tool?
NLTK
SpaCy
Orange Data Mining
Python
What is the primary goal of the "Test Yourself" questions mentioned in the document?
To introduce new concepts.
To demonstrate the use of no-code tools.
To review the user's understanding of the topic.
To provide examples of NLP applications.
What is the purpose of the log function in the TFIDF formula?
To make the calculation faster.
To prevent the IDF value from becoming too large and to scale it.
To make the TF value larger.
To calculate the frequency of words.
What is the final output of the text processing pipeline that leads to the Bag of Words model?
A list of all documents.
A document vector table with word frequencies.
The original text with stop words removed.
A set of grammatical rules.
What is the primary purpose of Natural Language Processing (NLP)?
Create fonts and layouts for digital documents
Build faster computer hardware for text tasks
Enable computers to understand and process human language
Translate human languages to numbers only
Which statement best describes natural languages over time?
They remain fixed without any change
They change and evolve over time
They are defined only by dictionaries
They follow strict mathematical rules
What do autogenerated captions primarily do in videos?
Convert images into spoken words
Summarize long videos into notes
Turn speech into text in real time
Translate text between languages
What is syntactic analysis (parsing) mainly used to check?
Real‑world relevance of statements
Emotional tone of the sentence
Speaker identity in audio clips
Grammar and logical structure of sentences
During semantic analysis, what is checked in the input text?
Only punctuation and spacing
Only the order of words in a sentence
Speaker intent beyond the literal text
Meaning of words and phrases for sense
Pragmatic analysis focuses on which aspect of a sentence?
Real‑world relevance and intended meaning
Converting uppercase to lowercase letters
Literal dictionary meaning only
Counting unique words and their frequency
What is a corpus in NLP?
A tool for tagging parts of speech
A single paragraph of text data
A collection of written texts combined
A list of stop words for removal
What does tokenization do in text processing?
Labels sentences with their sentiment
Combines many documents into one
Divides text into smaller units called tokens
Removes rare words from the dataset
Which best defines stop words in text analysis?
Rare words that carry deep meaning
Proper nouns requiring special handling
All words shorter than four letters
Very frequent words adding little meaning
Which statement correctly contrasts lemmatization and stemming?
Stemming ensures valid words while lemmatization does not
Lemmatization returns meaningful lemmas while stemming may not
Both only remove vowels from the words
Both produce valid dictionary base forms
In a Bag of Words model, what matters for representing text?
Grammar and word order in sentences
Unique words and their frequencies
Synonyms and antonyms relationships
Speaker’s emotion and context
TFIDF stands for which phrase?
Total Frequency–Inverse Data Factor
Term Frequency–Inverse Document Frequency
Token Frequency–Indexed Document Factor
Text Feature–Inverse Data Frequency
Which is a common application of TFIDF?
Image segmentation and labeling
Document classification of text data
Compiling code to machine language
Encrypting network communications
Which platform is mentioned as no‑code for text analysis?
PyTorch AutoML app
MonkeyLearn web platform
TensorFlow Hub online tools
SpaCy desktop suite
What is a chatbot best described as?
A computer program simulating conversation
A web browser for searching data
A keyboard for faster text typing
A physical robot for workshops
Which action can chatbots perform for e‑commerce?
Manufacture products on assembly lines
Answer questions and generate sales leads
Control warehouse robots with sensors
Design product packaging automatically
What does a low IDF value for a word like “the” indicate?
It appears rarely in most documents
It appears in many documents overall
It always carries strong sentiment
It is a proper noun in the corpus
What is a lexicon in language processing?
A stop word list for filtering
A tool for ranking web search pages
A collection of words and phrases used
A grammar checker algorithm only
Why convert all text to a single case during preprocessing?
To make documents shorter in size
To detect sarcasm more accurately
To prevent treating case variants as different
To remove all punctuation completely
What does discourse integration aim to build across sentences?
A list of all rare vocabulary words
A coherent story linking sentences
Randomized word order for variety
A map of part‑of‑speech tags
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): The TFIDF value of a word like "the" in a large corpus is typically low. Reason (R): The IDF component of TFIDF gives a low value to words that appear frequently across many documents.
Both A and R are true, but R is not the correct explanation of A.
Both A and R are true, and R is the correct explanation of A.
A is false, but R is true.
A is true, but R is false.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): In the Bag of Words model, the sequence of words in a sentence is irrelevant. Reason (R): The model focuses on the frequency of words rather than their grammatical relationships or order.
A is true, but R is false.
Both A and R are true, but R is not the correct explanation of A.
A is false, but R is true.
Both A and R are true, and R is the correct explanation of A.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Stemming is generally faster than lemmatization. Reason (R): Stemming simply removes affixes without consulting a lexicon, whereas lemmatization ensures the resulting word is a meaningful one.
Both A and R are true, and R is the correct explanation of A.
A is false, but R is true.
A is true, but R is false.
Both A and R are true, but R is not the correct explanation of A.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Sentiment Analysis is a tool to determine the underlying emotion in a text. Reason (R): It helps to automatically detect emotions when customers interact with products, services, or brands.
Both A and R are true, and R is the correct explanation of A.
Both A and R are true, but R is not the correct explanation of A.
A is true, but R is false.
A is false, but R is true.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): The final stage of NLP is Pragmatic Analysis. Reason (R): Pragmatic Analysis checks the grammatical correctness of a sentence.
Both A and R are true, and R is the correct explanation of A.
Both A and R are true, but R is not the correct explanation of A.
A is true, but R is false.
A is false, but R is true.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Converting text to a common case is an important step in text normalization. Reason (R): It ensures that the machine treats words like "Apple" and "apple" as the same entity.
A is false, but R is true.
A is true, but R is false.
Both A and R are true, but R is not the correct explanation of A.
Both A and R are true, and R is the correct explanation of A.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): A high TFIDF value for a word indicates that it is very important for a specific document. Reason (R): The word has a high term frequency in that document but a low document frequency across the entire corpus.
Both A and R are true, and R is the correct explanation of A.
A is false, but R is true.
Both A and R are true, but R is not the correct explanation of A.
A is true, but R is false.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Discourse Integration is the process of breaking down a large text into paragraphs, sentences, and words. Reason (R): Discourse Integration forms a coherent "story" by checking the relationship between successive sentences.
A is false, but R is true.
A is true, but R is false.
Both A and R are true, but R is not the correct explanation of A.
Both A and R are true, and R is the correct explanation of A.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Chatbots use NLP to simulate human conversation. Reason (R): NLP enables computers to understand and process human language, which is essential for a chatbot to function effectively.
Both A and R are true, and R is the correct explanation of A.
Both A and R are true, but R is not the correct explanation of A.
A is true, but R is false.
A is false, but R is true.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Semantic Analysis checks the meaningfulness of an input text. Reason (R): It is the first stage of the NLP pipeline, followed by Lexical Analysis.
A is true, but R is false.
A is false, but R is true.
Both A and R are true, but R is not the correct explanation of A.
Both A and R are true, and R is the correct explanation of A.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Autogenerated captions are a real-world application of NLP. Reason (R): NLP enables the conversion of speech into text in real-time.
Both A and R are true, and R is the correct explanation of A.
A is true, but R is false.
Both A and R are true, but R is not the correct explanation of A.
A is false, but R is true.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): The Bag of Words model is a method for text representation that retains the grammatical structure of sentences. Reason (R): The model disregards the sequence and grammar of words, focusing only on their frequency.
Both A and R are true, but R is not the correct explanation of A.
Both A and R are true, and R is the correct explanation of A.
A is true, but R is false.
A is false, but R is true.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): The process of breaking a large body of text into smaller units like words and sentences is called Tokenization. Reason (R): Tokenization is a key step in Text Normalization, which simplifies textual data.
Both A and R are true, and R is the correct explanation of A.
A is true, but R is false.
A is false, but R is true.
Both A and R are true, but R is not the correct explanation of A.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): NLTK is considered a "no-code" NLP tool. Reason (R): NLTK is a Python library that requires programming knowledge to be used for text processing.
A is true, but R is false.
A is false, but R is true.
Both A and R are true, but R is not the correct explanation of A.
Both A and R are true, and R is the correct explanation of A.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Keyword Extraction is used to automatically identify the most important words from a text. Reason (R): It helps provide valuable insights into the main topics or themes of a document.
Both A and R are true, and R is the correct explanation of A.
Both A and R are true, but R is not the correct explanation of A.
A is false, but R is true.
A is true, but R is false.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): A word with a high TFIDF value is typically a stop word. Reason (R): A high TFIDF value indicates that the word is rare in the corpus but has a high frequency in a specific document.
A is true, but R is false.
Both A and R are true, but R is not the correct explanation of A.
Both A and R are true, and R is the correct explanation of A.
A is false, but R is true.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): The Syntactic Analysis stage of NLP checks for the meaningfulness of a sentence. Reason (R): Semantic Analysis, not Syntactic Analysis, is responsible for checking if a sentence is meaningful.
Both A and R are true, but R is not the correct explanation of A.
A is false, but R is true.
A is true, but R is false.
Both A and R are true, and R is the correct explanation of A.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Natural languages are static and do not change over time. Reason (R): One of the features of natural languages is that they are constantly changing and evolving.
A is false, but R is true.
A is true, but R is false.
Both A and R are true, but R is not the correct explanation of A.
Both A and R are true, and R is the correct explanation of A.
Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): A script-bot is an AI-powered chatbot that can learn from user interactions. Reason (R): Script-bots are limited to a pre-defined set of scripted responses.
Both A and R are true, but R is not the correct explanation of A.
A is false, but R is true.
A is true, but R is false.
Both A and R are true, and R is the correct explanation of A.
Which statement best describes a high TF-IDF value for a word in a document?
Appears often in this document but rare in corpus
Appears rarely and common across corpus
Appears equally across documents and corpus
Appears often across corpus but rare in document
Which NLP stage primarily checks the meaningfulness of an input text?
Speech Recognition
Discourse Integration
Semantic Analysis
Lexical Analysis
In Discourse Integration, what is mainly examined to form a coherent story?
Word frequency within one sentence
Order of letters in every word
Length of each paragraph
Relationships between adjacent sentences
What is a core limitation of the Bag of Words model?
Cannot handle rare words at all
Ignores grammatical structure and word order
Requires labeled training data
Only works with spoken language
What does tokenization do during text processing?
Converts audio to text
Breaks text into smaller units called tokens
Assigns parts of speech to every token
Removes stopwords from the corpus
Which best describes text normalization in NLP?
Cleaning and simplifying text for processing
Rendering text as spoken audio output
Predicting next words in a sentence
Encrypting messages for secure transfer
What is the primary goal of keyword extraction?
Generate longer summaries from short notes
Translate sentences between human languages
Sort documents alphabetically by title
Identify main terms that capture document themes
In a corpus, what does the IDF component of TF‑IDF indicate?
Rarity of a word across many documents
Length of a sentence within one document
Order of words inside a single sentence
Grammar correctness of the entire corpus
Which operation is commonly part of text normalization?
Converting all text to lowercase case
Counting the number of pages
Applying data compression algorithms
Embedding watermarks in files
Stemming and lemmatization are used to:
Reduce words to base forms for analysis
Translate words into phonetic spelling
Encrypt vocabulary for secure storage
Detect sarcasm in social media posts
Which statement about Bag of Words is accurate?
Represents text by word frequencies, ignoring order
Stores meanings using a predefined ontology
Encodes grammar rules for sentence generation
Tracks word positions to preserve full sequence
Why convert text to a common case like lowercase?
Avoid treating same words as different tokens
Comply with hardware voltage limitations
Increase the speed of internet connectivity
Improve image clarity in scanned documents
Which example best shows context ambiguity?
The date "2024" meaning a calendar year
The word "triangle" meaning a polygon
The number "two" meaning exactly two
The word "red" meaning color or emotion
What does a chatbot mainly do in NLP applications?
Draws charts from numeric spreadsheet cells
Measures internet latency for diagnostics
Simulates human conversation to assist users
Compiles source code into machine binaries
Which difference between script‑bots and smart‑bots is correct?
Script‑bots use fixed replies; smart‑bots learn
Both learn continuously from every dialogue
Smart‑bots ignore context; script‑bots model it
Script‑bots are only voice; smart‑bots only text
Which best defines a corpus in text processing?
Entire collection of documents for analysis
Printed dictionary used by linguists
Single sentence chosen for demonstration
Encrypted archive for long‑term backups
How do voice assistants like Alexa use NLP?
Process speech to understand intent and act
Render videos by enhancing audio playback
Design microchips using logical circuits
Detect malware by scanning network packets
Which outcome distinguishes lemmatization from stemming?
Converts words to phonetic syllables
Removes all vowels from each token
Always yields longer word variants
Produces meaningful dictionary lemmas
What key limitation of Bag of Words should students recall?
Fails to count repeated words in texts
Requires labeled data for supervised learning
Only works on languages without inflection
Ignores word order and sequence information
Which task is best served by keyword extraction in a news app?
Predict stock prices from trading volumes
Tag each article with main topics quickly
Render headlines into artistic fonts
Compress images to reduce bandwidth
Which statement about TF‑IDF weights is most accurate?
High when terms are frequent in a document but rare in corpus
High when terms are common stop words across the entire corpus
Independent of term frequency within the specific document
Zero for every term that appears in any document of the corpus
Which step is NOT part of the Bag of Words workflow described?
Aggregate rows into a document vector table
Create document vectors for word counts
Train a neural network for embeddings
Create a dictionary of unique words
Build a final table of document frequencies
In Bag of Words, what does a document vector table primarily contain?
Syntactic parse trees for documents
Sentiment labels for each sentence
Frequencies of unique words per document
Entity types linked to each token
Topic labels predicted for each file
What is the main purpose of stop word removal during normalization?
Normalize numbers into a common scale
Add context from neighboring sentences
Increase the vocabulary size significantly
Focus on more meaningful terms in text
Convert words to their base dictionary form
Which pair correctly lists no-code tools and code-based tools?
SpaCy and Orange; NLTK and MonkeyLearn
Orange and MonkeyLearn; NLTK and SpaCy
NLTK and Orange; SpaCy and MonkeyLearn
NLTK and SpaCy; Orange and MonkeyLearn
MonkeyLearn and SpaCy; NLTK and Orange
In TF-IDF, why is a logarithm used in the IDF calculation?
To scale down extreme IDF values
To remove negative term frequencies
To convert counts into probabilities
To boost common words exponentially
To average TF across all documents
Which feature is NOT listed as a property of natural languages?
Structured with semantics for sentences
Deterministic with fixed meanings always
Dynamic and evolving over time
Redundant with multiple phrasing options
Governed by rules like syntax and lexicon
Syntactic analysis primarily checks what in NLP?
Grammatical structure and relationships
Speaker intent across conversations
Document-level topic distributions
Real-world relevance and sarcasm
Frequency of rare words globally
Semantic analysis verifies that words and phrases are
Aligned to speaker’s real intent
Weighted by inverse document frequency
Used meaningfully within the sentence
Linked to named entities correctly
Statistically independent across tokens
Text normalization is important mainly because it
Detects topics without labeled data
Adds new words to the corpus automatically
Translates documents into other languages
Simplifies text for later processing steps
Generates embeddings from character n-grams
Which is NOT an application of TF-IDF listed in the material?
Document classification by content importance
Topic modeling to find central themes
Information retrieval to rank relevant terms
Speech recognition for phoneme timing
Highlighting unique words in a corpus
A chatbot processes user input through stages including
Supervised, unsupervised, reinforcement
Lexical, syntactic, semantic, discourse, pragmatic
Optical, acoustic, visual, spatial, tactile
Token, lemma, stem, root, morpheme only
Heuristic, genetic, simulated annealing
A higher final TF-IDF value for a word suggests it is
Weighted down by high document counts
Only frequent within the entire corpus
Irrelevant due to low term frequency
Important in a document but rare overall
Common everywhere and not informative
Why is context important in NLP, as shown by the word “red”?
Context guarantees literal interpretation
Context only affects punctuation decisions
Context can change a word’s intended meaning
Context removes the need for tokenization
Context assigns a fixed universal meaning
Text classification mainly
Translates texts into target languages
Assigns texts to predefined categories
Generates summaries from long articles
Clusters texts without categories
Parses texts into dependency trees
During normalization, removing special characters and numbers is done to
Create new stemming dictionaries
Ensure all tokens are stop words
Preserve email IDs in every dataset
Eliminate tokens not useful for analysis
Increase the corpus size intentionally
Pragmatic analysis focuses on
Literal meaning only within grammar
Real-world intent beyond literal text
Counting words across documents
Generating the final document vector
Assigning parts of speech to tokens
Keyword extraction can help a business by
Translating posts into multiple languages
Automatically pulling key words and phrases
Encrypting customer feedback for privacy
Replacing human agents with chatbots
Measuring exact sentence grammar rules
In TF and DF, which statement is correct?
Both TF and DF are always equal values
DF measures occurrences within single file
TF is number of documents containing a term
TF counts across all documents globally
DF is number of documents where term appears
Why is stemming faster than lemmatization according to the material?
It ensures words become meaningful lemmas
It computes POS tags for each token
It expands words to original root forms
It checks a lexicon for valid lemmas
It removes affixes without dictionary checks
Which stage of an NLP pipeline identifies tokens like "The", "quick", and "brown" from a sentence?
Semantic meaning check
Pragmatic intent check
Lexical analysis of tokens
Syntactic grammar check
Discourse coherence check
In TF-IDF, what does the IDF component primarily do for very common words across documents?
Penalizes their importance
Raises their frequency
Ignores their occurrences
Duplicates their counts
Converts them to lowercase
During text normalization, which step removes words like "the", "is", and symbols before stemming?
Sentence segmentation step
Converting to common case
Tokenization into words
Removing stop words and symbols
Pragmatic analysis step
A chatbot built with fixed rules and unable to adapt beyond its script is best described as a:
Context-bot with plans
Neural-bot with vision
Hybrid-bot with memory
Smart-bot with learning
Script-bot with rules
Given TF=3 for word "game" in a document and IDF=log(10/2), which expression equals its TF-IDF?
log(3 × 10/2)
3 × log(2/10)
3 + log(10/2)
log(10/2) ÷ 3
3 × log(10/2)
After normalization steps, which lemmatized token list best matches Document 2: "Akash likes to play football, but Ajay prefers to play online games"?
[akash, likes, to, play, football, ajay, prefers, to, play, online, games]
[akash, like, to, plays, football, ajay, prefer, online, gaming]
[akash, like, to, play, football, ajay, prefer, to, play, online, game]
[Akash, like, play, football, Ajay, prefer, play, game]
[akash, ajay, best, friend]
After preprocessing the corpus [D1: "Aman and Avni are stressed", D2: "Aman went to a therapist", D3: "Avni went to download a health chatbot"], which set correctly represents the dictionary (unique words) for a Bag of Words model when lowercase conversion and stop-word removal are applied?
{aman, avni, stressed, went, therapist, download, health, chatbot}
{aman, avni, stressed, are, went, to, therapist, health}
{Aman, Avni, stressed, went, therapist, download, health, chatbot}
{aman, avni, are, went, to, therapist, download, chatbot}
Which vector correctly represents Document 1 in the created Bag of Words vectors using the dictionary order [aman, avni, stressed, went, therapist, download, health, chatbot]?
[1, 0, 1, 0, 1, 0, 0, 0]
[1, 0, 0, 1, 0, 0, 0, 0]
[1, 1, 1, 0, 0, 0, 0, 0]
[0, 1, 0, 1, 0, 1, 1, 1]
Which statement best explains why TFIDF helps with stop word filtering in text processing?
Common words have high DF so low TFIDF values
Rare words have high DF so high TFIDF values
Common words have low DF so high TFIDF values
Rare words have low TF so low TFIDF values
Given the corpus of four documents where the word "Papa" appears in three documents and appears once in Document 2, which TFIDF value for "Papa" in Document 2 is closest when using TFIDF = TF × log(Total Docs / Docs with term)?
0.333
0.000
1.333
0.125
NLP stands for ________.
None of the above
None Language Processing
Nature Language Processing
Natural Language Processing
__________, is the sub-field of AI that is focused on enabling computers to understand and process human languages.
Computer Vision
None of the above
Data Science
Natural Language Processing
__________ is the sub-field of AI that make the interactions between computers and human (natural) languages
None of the above
Natural Language Processing
Computer Vision
Data Science
Which of the games below is related to natural language processing?
Voice Assistants
Chatbots
Mystery Animal
Grammar Checkers
Applications of Natural Language Processing
Automatic Summarization
All of the above
Text Classification
Sentiment Analysis
__________ Information overload is a real problem when we need to access a specific, important piece of information from a huge knowledge base.
All of the above
Text Classification
Sentiment Analysis
Automatic Summarization
__________ is especially relevant when used to provide an overview of a news item or blog post, while avoiding redundancy from multiple sources and maximizing the diversity of content obtained.
All of the above
Automatic Summarization
Sentiment Analysis
Text Classification
The goal of sentiment analysis is to identify sentiment among several posts or even in the same post where emotion is not always explicitly expressed.
Automatic Summarization
Sentiment Analysis
Text Classification
All of the above
Companies use Natural Language Processing applications, such as __________, to identify opinions and sentiment online to help them understand what customers think about their products and services
Automatic Summarization
Sentiment Analysis
Text Classification
All of the above
__________ makes it possible to assign predefined categories to a document and organize it to help you find the information you need or simplify some activities.
Text Classification
Sentiment Analysis
Automatic Summarization
All of the above
__________ device helps to communicate with humans and abilities to make humans lives easier.
Siri
Google Assistant
All of the above
Cortana
__________ is all about how machines try to understand and interpret human language and operate accordingly.
None of the above
Computer Vision
Data Science
Natural Language Processing
By dividing up large problems into smaller ones, __________ aims to help you manage them in a more constructive manner.
CDP
CLP
CBT
CSP
CBT stands for ___________.
Common Behavioural Therapy (CBT)
Cognitive Behavioural Therapy (CBT)
None of the above
Connection Behavioural Therapy (CBT)
Cognitive behavioural Therapy includes __________.
Your Thoughts
All of the above
Your Behaviors
Your Emotions
