Artificial Intelligence

CBSE Class 10 AI Unit 6 MCQs with Answers & Explanations (2026–27) | Natural Language Processing

Class 10 · Artificial Intelligence

Preparing for the CBSE Class 10 Artificial Intelligence (Code 417) examination? This comprehensive collection of 50 Multiple Choice Questions (MCQs) from Unit 6 – Natural Language Processing (NLP) is designed according to the latest CBSE 2026–27 syllabus.

These MCQs cover all important concepts including Natural Language Processing, Natural Language vs Computer Language, applications of NLP, NLP pipeline, chatbots, text preprocessing, tokenization, stop words, stemming, lemmatization, Bag of Words (BoW), TF-IDF, sentiment analysis, text classification, and competency-based questions with detailed explanations.

Each question includes:

  • ✔ Correct Answer
  • ✔ Detailed Explanation
  • ✔ Why the Other Options are Incorrect
  • ✔ CBSE Exam-Oriented Approach

? Topics Covered

  • Introduction to Natural Language Processing (NLP)
  • Natural Language vs Computer Language
  • Features of Natural Language
  • Applications of NLP
  • NLP Analysis Stages
  • Chatbots
  • Corpus and Text Normalization
  • Tokenization
  • Stop Words
  • Case Conversion
  • Stemming
  • Lemmatization
  • Bag of Words (BoW)
  • TF-IDF
  • Orange Data Mining
  • MonkeyLearn
  • CBSE Competency-Based Questions

? Exam Tip: CBSE frequently asks application-based and competency-based questions from NLP. Focus on understanding the differences between Tokenization, Stemming, Lemmatization, Bag of Words, TF-IDF, Chatbots, and Sentiment Analysis rather than memorizing definitions.

CBSE Class 10 AI Unit 6 MCQs with Answers

MCQs 1–10

Q1. What is a Natural Language?

A. A language used only for computer programming
B. A language such as English, Hindi, or French used by humans
C. A binary language understood by computers
D. A language used only by robots

Show Answer & Explanation

Correct Answer: B. A language such as English, Hindi, or French used by humans

Explanation: Natural languages are human languages that have evolved naturally over time, such as English, Hindi, Spanish, and French.

Why other options are incorrect:

  • A. Programming languages are computer languages, not natural languages.
  • C. Binary language is understood by computers.
  • D. Robots do not have their own natural language.

Q2. Which feature of Natural Language allows the same information to be expressed in different ways?

A. Syntax
B. Lexicon
C. Redundancy
D. Compilation

Show Answer & Explanation

Correct Answer: C. Redundancy

Explanation: Natural languages are redundant, meaning the same idea can be communicated using different words or sentence structures.

Why other options are incorrect:

  • A. Syntax refers to grammatical structure.
  • B. Lexicon means the collection of words in a language.
  • D. Compilation is related to programming languages.

Q3. Why is context important in Natural Language Processing?

A. It increases internet speed.
B. A word may have different meanings depending on the sentence.
C. It removes punctuation marks.
D. It converts text into binary.

Show Answer & Explanation

Correct Answer: B. A word may have different meanings depending on the sentence.

Explanation: NLP uses context to determine the correct meaning of words because many words have multiple meanings.

Why other options are incorrect:

  • A. Context has nothing to do with internet speed.
  • C. Removing punctuation is part of preprocessing.
  • D. NLP does not convert text into binary.

Q4. Computer languages such as Python and Java are mainly used to:

A. Communicate naturally with humans
B. Interact with computer systems
C. Replace human languages
D. Create dictionaries

Show Answer & Explanation

Correct Answer: B. Interact with computer systems

Explanation: Programming languages like Python and Java are designed to communicate instructions to computers.

Why other options are incorrect:

  • A. Human communication uses natural languages.
  • C. Programming languages cannot replace human languages.
  • D. They are not used for creating dictionaries.

Q5. Which NLP application converts spoken words into text automatically?

A. Sentiment Analysis
B. Auto-generated Captions
C. Keyword Extraction
D. Machine Vision

Show Answer & Explanation

Correct Answer: B. Auto-generated Captions

Explanation: Auto-generated captions use speech recognition to convert spoken language into text.

Why other options are incorrect:

  • A. Sentiment Analysis identifies emotions in text.
  • C. Keyword Extraction identifies important words.
  • D. Machine Vision belongs to Computer Vision.

Q6. "Hey Siri, set an alarm for 6 AM." is an example of interacting with a:

A. Spreadsheet
B. Voice Assistant
C. Database Server
D. Compiler

Show Answer & Explanation

Correct Answer: B. Voice Assistant

Explanation: Siri, Alexa, and Google Assistant use NLP to understand voice commands and perform tasks.

Why other options are incorrect:

  • A. A spreadsheet cannot process voice commands.
  • C. Database servers store data.
  • D. A compiler translates source code.

Q7. What is the primary purpose of Sentiment Analysis?

A. Translate languages
B. Identify positive, negative, or neutral opinions in text
C. Compress text files
D. Detect image objects

Show Answer & Explanation

Correct Answer: B. Identify positive, negative, or neutral opinions in text

Explanation: Sentiment Analysis determines the emotional tone or opinion expressed in textual data.

Why other options are incorrect:

  • A. Translation is a separate NLP application.
  • C. Compression is unrelated.
  • D. Object detection belongs to Computer Vision.

Q8. Grouping news articles into categories such as Sports, Politics, or Business is known as:

A. Tokenization
B. Text Classification
C. Parsing
D. Stemming

Show Answer & Explanation

Correct Answer: B. Text Classification

Explanation: Text Classification automatically assigns documents to predefined categories.

Why other options are incorrect:

  • A. Tokenization splits text into tokens.
  • C. Parsing checks grammar.
  • D. Stemming removes prefixes or suffixes.

Q9. Which stage of NLP divides large text into paragraphs, sentences, and words?

A. Lexical Analysis
B. Semantic Analysis
C. Pragmatic Analysis
D. Discourse Integration

Show Answer & Explanation

Correct Answer: A. Lexical Analysis

Explanation: Lexical Analysis identifies the structure of text by dividing it into meaningful units.

Why other options are incorrect:

  • B. Semantic Analysis checks meaning.
  • C. Pragmatic Analysis identifies intended meaning.
  • D. Discourse Integration establishes relationships among sentences.

Q10. Syntactic Analysis is mainly concerned with:

A. Grammar of sentences and phrases
B. Image recognition
C. Database indexing
D. Video processing

Show Answer & Explanation

Correct Answer: A. Grammar of sentences and phrases

Explanation: Syntactic Analysis (Parsing) verifies grammatical correctness and the relationship among words in a sentence.

Why other options are incorrect:

  • B. Image recognition belongs to Computer Vision.
  • C. Database indexing is unrelated to NLP.
  • D. Video processing is outside the scope of NLP.

MCQs 11–20

Q11. Why would an NLP system reject the phrase "hot ice cream" during Semantic Analysis?

A. Because the sentence is grammatically incorrect.
B. Because the words are not in the dictionary.
C. Because the phrase is not meaningful in the real world.
D. Because it contains punctuation marks.

Show Answer & Explanation

Correct Answer: C. Because the phrase is not meaningful in the real world.

Explanation: Semantic Analysis checks whether a sentence makes logical sense. Although "hot ice cream" is grammatically correct, it is semantically meaningless.

Why other options are incorrect:

  • A. The grammar is correct.
  • B. Both words exist in the dictionary.
  • D. Punctuation has no role here.

Q12. Which stage of NLP establishes relationships between consecutive sentences to form a meaningful story?

A. Lexical Analysis
B. Syntactic Analysis
C. Discourse Integration
D. Tokenization

Show Answer & Explanation

Correct Answer: C. Discourse Integration

Explanation: Discourse Integration ensures that consecutive sentences are logically connected and form a coherent passage.

Why other options are incorrect:

  • A. Lexical Analysis identifies words and phrases.
  • B. Syntactic Analysis checks grammar.
  • D. Tokenization splits text into tokens.

Q13. Pragmatic Analysis is mainly used to identify:

A. The grammatical structure of a sentence
B. The intended meaning of a sentence
C. The number of words in a document
D. Stop words in text

Show Answer & Explanation

Correct Answer: B. The intended meaning of a sentence

Explanation: Pragmatic Analysis considers the speaker's intention and context to determine the actual meaning of a sentence.

Why other options are incorrect:

  • A. Grammar is checked during Syntactic Analysis.
  • C. Word counting is unrelated.
  • D. Stop words are handled during preprocessing.

Q14. A computer program that simulates human conversation is called a:

A. Compiler
B. Chatbot
C. Kernel
D. Dataset

Show Answer & Explanation

Correct Answer: B. Chatbot

Explanation: A chatbot is an AI application that interacts with users using text or voice conversations.

Why other options are incorrect:

  • A. A compiler translates source code.
  • C. A kernel is used in Computer Vision.
  • D. A dataset is a collection of data.

Q15. What is the main characteristic of a Script Bot?

A. It continuously learns from new data.
B. It follows predefined scripts or rules.
C. It performs deep learning automatically.
D. It has unlimited conversational ability.

Show Answer & Explanation

Correct Answer: B. It follows predefined scripts or rules.

Explanation: Script Bots work according to predefined rules and responses, making them simple but less flexible.

Why other options are incorrect:

  • A. Learning from data is a feature of Smart Bots.
  • C. Script Bots do not perform deep learning.
  • D. Their functionality is limited.

Q16. Compared to Script Bots, Smart Bots are:

A. Less flexible
B. Able to learn from more data and improve over time
C. Unable to understand natural language
D. Limited to one predefined response

Show Answer & Explanation

Correct Answer: B. Able to learn from more data and improve over time

Explanation: Smart Bots use Artificial Intelligence and Machine Learning to understand user input and continuously improve their responses.

Why other options are incorrect:

  • A. Smart Bots are more flexible.
  • C. They are designed to understand natural language.
  • D. They can generate different responses.

Q17. In NLP, the term "Corpus" refers to:

A. A single sentence
B. A collection of textual documents
C. A chatbot program
D. A dictionary only

Show Answer & Explanation

Correct Answer: B. A collection of textual documents

Explanation: A Corpus is a complete collection of text documents used for training and analyzing NLP models.

Why other options are incorrect:

  • A. A corpus contains many documents.
  • C. It is not a chatbot.
  • D. A dictionary is only one resource within NLP.

Q18. Text Normalization is performed to:

A. Increase text complexity
B. Reduce the complexity of textual data
C. Convert text into images
D. Translate programming languages

Show Answer & Explanation

Correct Answer: B. Reduce the complexity of textual data

Explanation: Text Normalization simplifies text so that it becomes easier for machines to process and analyze.

Why other options are incorrect:

  • A. The objective is simplification.
  • C. Text is not converted into images.
  • D. Programming languages are unrelated.

Q19. The process of breaking text into smaller units such as words is called:

A. Lemmatization
B. Tokenization
C. Parsing
D. Classification

Show Answer & Explanation

Correct Answer: B. Tokenization

Explanation: Tokenization divides text into smaller units called tokens, such as words or sentences.

Why other options are incorrect:

  • A. Lemmatization converts words to their dictionary form.
  • C. Parsing checks grammar.
  • D. Classification groups documents.

Q20. Which of the following is an example of a Stop Word?

A. Elephant
B. Chatbot
C. The
D. Python

Show Answer & Explanation

Correct Answer: C. The

Explanation: Stop words are commonly occurring words such as "the", "a", "is", and "and" that usually contribute little to the meaning of a sentence.

Why other options are incorrect:

  • A. "Elephant" is a meaningful content word.
  • B. "Chatbot" is an important keyword.
  • C. "The" is one of the most common stop words.
  • D. "Python" is a significant term, not a stop word.

MCQs 21–30

Q21. Why is text converted to lowercase during Text Normalization?

A. To improve grammar
B. To ensure words like "Hello" and "hello" are treated as the same word
C. To remove punctuation marks
D. To translate text into another language

Show Answer & Explanation

Correct Answer: B. To ensure words like "Hello" and "hello" are treated as the same word

Explanation: Converting text to lowercase avoids treating the same word with different cases as separate words, improving consistency.

Why other options are incorrect:

  • A. Lowercasing does not improve grammar.
  • C. Punctuation removal is a separate preprocessing step.
  • D. Lowercasing does not perform translation.

Q22. What is Stemming?

A. Translating text into another language
B. Removing prefixes or suffixes to obtain the root form of a word
C. Checking grammatical correctness
D. Counting the number of words in a document

Show Answer & Explanation

Correct Answer: B. Removing prefixes or suffixes to obtain the root form of a word

Explanation: Stemming reduces words to their root form by removing prefixes or suffixes. For example, healing → heal.

Why other options are incorrect:

  • A. Translation is a different NLP application.
  • C. Grammar checking is performed during parsing.
  • D. Word counting is unrelated to stemming.

Q23. Which is a limitation of Stemming?

A. It always produces meaningful words.
B. The resulting root word may not be meaningful.
C. It cannot process English text.
D. It only works on images.

Show Answer & Explanation

Correct Answer: B. The resulting root word may not be meaningful.

Explanation: Stemming simply removes affixes and may produce words such as "studi", which are not valid dictionary words.

Why other options are incorrect:

  • A. This is a feature of Lemmatization, not Stemming.
  • C. Stemming is commonly used with English text.
  • D. Stemming works on text, not images.

Q24. How is Lemmatization different from Stemming?

A. It is faster than stemming.
B. It always produces meaningful dictionary words.
C. It removes punctuation only.
D. It works only on stop words.

Show Answer & Explanation

Correct Answer: B. It always produces meaningful dictionary words.

Explanation: Lemmatization converts words to their proper dictionary form (lemma), making the output meaningful.

Why other options are incorrect:

  • A. Lemmatization is generally slower than stemming.
  • C. Punctuation removal is a separate preprocessing step.
  • D. It is not limited to stop words.

Q25. The Bag of Words (BoW) model mainly provides:

A. Image labels
B. A vocabulary of unique words and their frequencies
C. Grammar correction
D. Speech recognition

Show Answer & Explanation

Correct Answer: B. A vocabulary of unique words and their frequencies

Explanation: Bag of Words creates a vocabulary of unique words from the corpus and records how frequently they appear.

Why other options are incorrect:

  • A. Image labels belong to Computer Vision.
  • C. BoW does not check grammar.
  • D. Speech recognition is another NLP application.

Q26. Which of the following is NOT a step in the Bag of Words algorithm?

A. Text preprocessing
B. Creating a dictionary of unique words
C. Creating document vectors
D. Identifying pixel values of characters

Show Answer & Explanation

Correct Answer: D. Identifying pixel values of characters

Explanation: Pixel values are related to Computer Vision, whereas Bag of Words is a text-processing technique.

Why other options are incorrect:

  • A. Text preprocessing is an important BoW step.
  • B. A unique dictionary is created in BoW.
  • C. Document vectors are generated in the final stage.

Q27. A Document Vector is:

A. A summary of a document
B. A numerical representation showing the occurrence of words in a document
C. A chatbot conversation
D. A translated document

Show Answer & Explanation

Correct Answer: B. A numerical representation showing the occurrence of words in a document

Explanation: Document Vectors represent documents numerically by indicating whether and how many times each vocabulary word appears.

Why other options are incorrect:

  • A. It is not a text summary.
  • C. Chatbots are separate NLP applications.
  • D. Translation is unrelated.

Q28. In the Bag of Words model, words with the highest frequency are usually:

A. Rare words
B. Stop words with low information value
C. Technical terms
D. Keywords only

Show Answer & Explanation

Correct Answer: B. Stop words with low information value

Explanation: Frequently occurring words such as "the", "is", and "and" carry very little useful information and are generally removed.

Why other options are incorrect:

  • A. Rare words occur less frequently.
  • C. Technical terms are not necessarily frequent.
  • D. Keywords are usually informative words.

Q29. Which type of words generally provides the highest information value in a corpus?

A. Stop words
B. Frequent grammatical words
C. Rare and meaningful words
D. Punctuation marks

Show Answer & Explanation

Correct Answer: C. Rare and meaningful words

Explanation: Rare words often carry the most useful information because they help identify the subject or context of a document.

Why other options are incorrect:

  • A. Stop words contribute little meaning.
  • B. Frequent grammatical words have low information value.
  • D. Punctuation marks are not informative.

Q30. TF-IDF stands for:

A. Total Frequency and Internal Data Format
B. Term Frequency and Inverse Document Frequency
C. Text File Integrated Database Framework
D. Token Frequency and Information Data Flow

Show Answer & Explanation

Correct Answer: B. Term Frequency and Inverse Document Frequency

Explanation: TF-IDF is a statistical technique that measures the importance of a word in a document relative to the entire corpus.

Why other options are incorrect:

  • A. Incorrect expansion.
  • C. This is not the full form of TF-IDF.
  • D. Incorrect expansion.

MCQs 31–40

Q31. Term Frequency (TF) refers to:

A. The total number of documents in a corpus
B. The number of times a word appears in a document
C. The number of unique words in a corpus
D. The total number of stop words

Show Answer & Explanation

Correct Answer: B. The number of times a word appears in a document

Explanation: Term Frequency (TF) measures how frequently a particular word occurs within a single document.

Why other options are incorrect:

  • A. This refers to the corpus, not TF.
  • C. Unique words form the vocabulary.
  • D. Stop words are unrelated to TF.

Q32. Document Frequency (DF) is defined as:

A. The number of times a word appears in one document
B. The number of documents containing a particular word
C. The number of unique words in a document
D. The number of sentences in a document

Show Answer & Explanation

Correct Answer: B. The number of documents containing a particular word

Explanation: Document Frequency counts how many documents in a corpus contain a specific word.

Why other options are incorrect:

  • A. This defines Term Frequency.
  • C. Vocabulary size is different.
  • D. Sentence count has no relation to DF.

Q33. A word receives a high TF-IDF score when it:

A. Appears frequently in one document but rarely in others
B. Appears in every document equally
C. Never appears in the document
D. Is always a stop word

Show Answer & Explanation

Correct Answer: A. Appears frequently in one document but rarely in others

Explanation: A high TF-IDF score indicates that a word is important in one document while being uncommon across the corpus.

Why other options are incorrect:

  • B. Common words receive lower TF-IDF scores.
  • C. A missing word has no importance in that document.
  • D. Stop words generally have very low TF-IDF values.

Q34. Which of the following is a common application of TF-IDF?

A. Face Detection
B. Information Retrieval Systems
C. Image Segmentation
D. Speech Recording

Show Answer & Explanation

Correct Answer: B. Information Retrieval Systems

Explanation: TF-IDF helps search engines and information retrieval systems identify the most relevant documents.

Why other options are incorrect:

  • A. Face Detection belongs to Computer Vision.
  • C. Image Segmentation is unrelated to NLP.
  • D. Speech recording does not use TF-IDF.

Q35. MonkeyLearn is an example of a:

A. Computer Vision camera
B. No-code NLP text analysis platform
C. Programming language
D. Database Management System

Show Answer & Explanation

Correct Answer: B. No-code NLP text analysis platform

Explanation: MonkeyLearn is a no-code platform used for text analysis tasks such as sentiment analysis, keyword extraction, and text classification.

Why other options are incorrect:

  • A. It is software, not a camera.
  • C. MonkeyLearn is not a programming language.
  • D. It is not a DBMS.

Q36. Which no-code platform can be used to perform Sentiment Analysis practically?

A. Orange Data Mining
B. MS Paint
C. Adobe Photoshop
D. VLC Media Player

Show Answer & Explanation

Correct Answer: A. Orange Data Mining

Explanation: Orange Data Mining provides several NLP widgets that allow users to perform sentiment analysis without writing code.

Why other options are incorrect:

  • B. MS Paint is an image editor.
  • C. Photoshop is used for image editing.
  • D. VLC is a media player.

Q37. Voice of the Customer (VoC) analysis helps organizations to:

A. Increase internet speed
B. Understand customer expectations and experiences
C. Translate customer reviews into code
D. Remove customer complaints automatically

Show Answer & Explanation

Correct Answer: B. Understand customer expectations and experiences

Explanation: Voice of the Customer analysis uses NLP techniques to analyze customer feedback and improve products and services.

Why other options are incorrect:

  • A. Internet speed is unrelated.
  • C. Customer reviews are analyzed, not converted into code.
  • D. NLP analyzes feedback but does not automatically remove complaints.

Q38. In a Document Vector, if a vocabulary word does not appear in a document, its value is:

A. 1
B. -1
C. 255
D. 0

Show Answer & Explanation

Correct Answer: D. 0

Explanation: In the Bag of Words model, a value of 0 indicates that the word does not occur in that document.

Why other options are incorrect:

  • A. 1 indicates one occurrence.
  • B. Negative values are not used.
  • C. 255 is unrelated to document vectors.

Q39. Assertion (A): All natural languages are redundancy-free.
Reason (R): Redundancy causes confusion in communication.

A. Both A and R are true, and R is the correct explanation of A.
B. A is true, but R is false.
C. Both A and R are true, but R is not the correct explanation of A.
D. Both A and R are false.

Show Answer & Explanation

Correct Answer: D. Both A and R are false.

Explanation: Natural languages are actually redundant. Redundancy helps humans understand messages even if some words are missed or unclear.

Why other options are incorrect:

  • A. The Assertion is false.
  • B. Both statements are false.
  • C. Neither statement is true.

Q40. Why is Discourse Integration important in NLP?

A. It checks spelling mistakes only.
B. It ensures that sentences are logically connected.
C. It counts stop words.
D. It converts text into speech.

Show Answer & Explanation

Correct Answer: B. It ensures that sentences are logically connected.

Explanation: Discourse Integration maintains the flow of ideas by connecting related sentences into a meaningful passage.

Why other options are incorrect:

  • A. Spell checking is a different task.
  • C. Stop-word counting is unrelated.
  • D. Text-to-speech is another NLP application.

MCQs 41–50

Q41. Which NLP application automatically identifies the most important words or phrases from a document?

A. Keyword Extraction
B. Tokenization
C. Stemming
D. Lemmatization

Show Answer & Explanation

Correct Answer: A. Keyword Extraction

Explanation: Keyword Extraction identifies the most significant words or phrases in a document, helping summarize content and understand customer opinions.

Why other options are incorrect:

  • B. Tokenization only splits text into tokens.
  • C. Stemming reduces words to their root form.
  • D. Lemmatization converts words into meaningful dictionary forms.

Q42. Elizabot and Mitsuku are examples of:

A. Voice Assistants
B. Chatbots
C. Search Engines
D. Operating Systems

Show Answer & Explanation

Correct Answer: B. Chatbots

Explanation: Elizabot and Mitsuku are well-known chatbots that simulate conversations with users using Natural Language Processing.

Why other options are incorrect:

  • A. Voice assistants primarily respond to spoken commands.
  • C. Search engines retrieve web pages.
  • D. Operating systems manage computer resources.

Q43. During text preprocessing, special characters such as '@' and '#' are generally:

A. Converted into numbers
B. Removed if they are not required
C. Converted into stop words
D. Replaced with spaces only

Show Answer & Explanation

Correct Answer: B. Removed if they are not required

Explanation: Special characters are usually removed during text preprocessing unless they carry useful information, such as in email addresses or hashtags.

Why other options are incorrect:

  • A. They are not converted into numbers.
  • C. Stop words are common words like "the" and "is".
  • D. They are generally removed rather than simply replaced with spaces.

Q44. What is the lemma of the word "studies"?

A. Studi
B. Studies
C. Study
D. Studied

Show Answer & Explanation

Correct Answer: C. Study

Explanation: Lemmatization converts a word into its meaningful dictionary form (lemma). Therefore, the lemma of "studies" is "study".

Why other options are incorrect:

  • A. "Studi" is a possible stem but not a valid dictionary word.
  • B. This is the original word.
  • D. "Studied" is another inflected form.

Q45. In the Bag of Words model, if a word appears twice in a document, its value in the document vector will be:

A. 0
B. 1
C. 2
D. -1

Show Answer & Explanation

Correct Answer: C. 2

Explanation: The document vector stores the frequency of each vocabulary word. If a word appears twice, its value becomes 2.

Why other options are incorrect:

  • A. 0 means the word is absent.
  • B. 1 represents one occurrence only.
  • D. Negative values are not used in Bag of Words.

Q46. What is a Lexicon?

A. A collection of words and phrases used in a language
B. A programming language
C. A chatbot database
D. A grammar-checking software

Show Answer & Explanation

Correct Answer: A. A collection of words and phrases used in a language

Explanation: A lexicon is the complete collection of words and phrases that belong to a language.

Why other options are incorrect:

  • B. A lexicon is not a programming language.
  • C. It is not a chatbot database.
  • D. Grammar-checking software uses a lexicon but is not itself a lexicon.

Q47. Topic Modeling is mainly used to:

A. Count pixels in an image
B. Identify the main topic of a collection of text
C. Improve image quality
D. Design chatbots

Show Answer & Explanation

Correct Answer: B. Identify the main topic of a collection of text

Explanation: Topic Modeling analyzes a corpus to discover the hidden themes or topics present in the documents.

Why other options are incorrect:

  • A. Pixel counting belongs to Computer Vision.
  • C. Image enhancement is unrelated.
  • D. Chatbot development is a different NLP application.

Q48. The objective of the "My Goodness" activity in the CBSE handbook is to:

A. Develop a chatbot
B. Understand how personal judgments and biases influence decisions
C. Learn Python programming
D. Build a sentiment analysis model

Show Answer & Explanation

Correct Answer: B. Understand how personal judgments and biases influence decisions

Explanation: The activity demonstrates that different people may make different decisions based on their experiences, beliefs, and biases.

Why other options are incorrect:

  • A. The activity is not about chatbot development.
  • C. It does not involve Python programming.
  • D. It is unrelated to building sentiment analysis models.

Q49. "Parsing" is another name for:

A. Lexical Analysis
B. Syntactic Analysis
C. Semantic Analysis
D. Pragmatic Analysis

Show Answer & Explanation

Correct Answer: B. Syntactic Analysis

Explanation: Parsing is the process of analyzing the grammatical structure of a sentence and is another name for Syntactic Analysis.

Why other options are incorrect:

  • A. Lexical Analysis identifies words.
  • C. Semantic Analysis checks meaning.
  • D. Pragmatic Analysis determines intended meaning.

Q50. Assertion (A): Machines can understand natural human language exactly like humans.
Reason (R): Natural Language Processing converts human language into a form that machines can process.

A. Both A and R are true, and R is the correct explanation of A.
B. A is false, but R is true.
C. Both A and R are true, but R is not the correct explanation of A.
D. A is true, but R is false.

Show Answer & Explanation

Correct Answer: B. A is false, but R is true.

Explanation: Machines do not naturally understand human language like humans. They require Natural Language Processing (NLP) techniques to convert language into a form they can analyze and process.

Why other options are incorrect:

  • A. The Assertion is false.
  • C. The Assertion is incorrect.
  • D. The Reason is true.

? Quick Revision

  • Natural Language is the language spoken and written by humans.
  • NLP (Natural Language Processing) enables computers to understand, interpret, and generate human language.
  • Applications of NLP include chatbots, voice assistants, language translation, sentiment analysis, keyword extraction, text classification, and auto-generated captions.
  • The five major stages of NLP are Lexical Analysis, Syntactic Analysis, Semantic Analysis, Discourse Integration, and Pragmatic Analysis.
  • Text Normalization includes case conversion, removing punctuation, removing stop words, tokenization, stemming, and lemmatization.
  • Bag of Words (BoW) converts text into numerical document vectors based on word frequencies.
  • TF-IDF identifies important words by considering both their frequency in a document and their rarity across the corpus.
  • Orange Data Mining and MonkeyLearn are popular no-code NLP tools.
  • Script Bots follow predefined rules, whereas Smart Bots learn from data and improve over time.
  • Focus on understanding concepts rather than memorizing definitions for CBSE competency-based questions.

? Exam Tip

For the CBSE Class 10 Artificial Intelligence (Code 417) examination, pay special attention to the differences between Tokenization, Stemming, Lemmatization, Bag of Words, TF-IDF, Script Bots, and Smart Bots. Also revise the five stages of NLP, applications such as Sentiment Analysis and Text Classification, and practice assertion-reason as well as competency-based questions, as these are commonly asked in the CBSE examination.