Class 10 Artificial Intelligence

Natural Language Processing

52 Class 10 Artificial Intelligence questions on Natural Language Processing from the CBSE board papers 2022–2026, each with its answer and a step-by-step solution.

Questions · page 3 of 3

1. Q41 CBSE 2023
   Define ​Chatbot. ​What ​are ​its ​types ?
   Show answer

   A chatbot is a program that converses with a person in human language; its two types are the script-bot and the smart-bot.

   A chatbot is a computer program that holds a conversation with a person in ordinary human language and answers questions or carries out tasks. Its two types are the script-bot, which follows a fixed script, and the smart-bot, which is flexible and powerful.

   Step-by-step solution →
2. Q42 CBSE 2023
   With ​reference to data processing, ​expand the ​term TFIDF. ​Also ​give any two applications of ​TFIDF.
   Show answer

   TFIDF is Term Frequency - Inverse Document Frequency; applications include document classification and information retrieval in search engines.

   TFIDF stands for Term Frequency - Inverse Document Frequency. Two of its applications are document classification and information retrieval in search engines; topic modelling and stop-word filtering are equally acceptable.

   Step-by-step solution →
3. Q43 CBSE 2023
   Create a ​document vector table from the following documents by implementing all ​the four ​steps of Bag of words model. Also depict the outcome of ​each step. Document 1 ​: Sameera and ​Sanya are classmates. Document 2 : Sameera likes dancing but Sanya loves to ​study mathematics.
   Show answer

   The 12-word dictionary gives the vectors $1,1,1,1,1,0,0,0,0,0,0,0$ for Document 1 and $1,0,1,0,0,1,1,1,1,1,1,1$ for Document 2.

   Step 1, text normalisation: both sentences are lower-cased, their full stops removed and the words tokenised; no stop word is dropped. Step 2, the dictionary holds the 12 unique words of the corpus: sameera, and, sanya, are, classmates, likes, dancing, but, loves, to, study, mathematics. Step 3, each dictionary word is counted in each document, giving a vector of 12 numbers per document. Step 4, the two vectors form the document vector table below.

   Step-by-step solution →
4. Q44 CBSE 2022
   What is NLP ?
   Show answer

   NLP is the sub-field of AI that enables computers to understand and process human languages.

   NLP (Natural Language Processing) is the sub-field of AI that enables computers to understand and process human languages, spoken or written.

   Step-by-step solution →
5. Q45 CBSE 2022
   Mention any ​two ​commonly used ​applications ​of ​NLP.
   Show answer

   Two applications of NLP are virtual assistants such as Siri and Alexa, and sentiment analysis of reviews.

   Two applications of NLP are virtual assistants (such as Siri and Alexa) and sentiment analysis of customer reviews.

   Step-by-step solution →
6. Q46 CBSE 2022
   Name any ​two ​currently popular virtual ​assistants.
   Show answer

   Google Assistant and Amazon Alexa are two popular virtual assistants.

   Step-by-step solution →
7. Q47 CBSE 2022
   Name ​the ​process ​of ​dividing ​whole corpus ​into ​sentences.
   Show answer

   The process is sentence segmentation.

   Sentence segmentation.

   Step-by-step solution →
8. Q48 CBSE 2022
   What is ​Tokenization ​? ​Count how many tokens are present in the following statement : I find ​that the ​harder I work, ​the more luck ​I seem to have.
   Show answer

   Tokenisation divides a sentence into tokens; the given statement has 16 tokens (14 words, one comma and one full stop).

   Tokenisation is the step of text normalisation in which each sentence is divided into tokens, every word, number and special character being a separate token. The given statement has 16 tokens: 14 words, one comma and one full stop.

   Step-by-step solution →
9. Q49 CBSE 2022
   Kaira, ​a ​beginner in the field ​of NLP is trying to understand the process of Stemming. ​Help her in filling up the ​following table ​by suggesting appropriate affixes and ​stem of the words mentioned ​there :

   S. No.	Word	Affixes	Stem
   i.	Tries
   ii.	Learning

   Show answer

   Tries has affix -es and stem tri; Learning has affix -ing and stem learn.

   (i) Tries: affix -es, stem tri. (ii) Learning: affix -ing, stem learn.

   Step-by-step solution →
10. Q50 CBSE 2022
    Explain ​the following picture which depicts one ​of the ​processes on NLP. Also mention ​the ​purpose which ​will be achieved ​by this ​process.

    Show answer

    The picture shows conversion to a common (lower) case in text normalisation, so the machine does not treat the same word as different words.

    The picture shows converting text to a common case, a step of text normalisation: all six forms of the word (HELLO, HeLlo, HELLo, hELLO, hElLO, HellO) are converted to lower case, hello. Purpose: the case-sensitive machine does not treat the same word as different words just because of its case.

    Step-by-step solution →
11. Q51 CBSE 2022
    Consider the text of following documents ​: Document 1 : Sahil likes to play cricket Document ​2 ​: Sajal likes cricket too Document ​3 : Sajal also likes to play basketball Apply all the four steps of ​Bag of words model ​of NLP ​on the above given documents and generate the output.
    Show answer

    The nine-word dictionary gives the vectors $1,1,1,1,1,0,0,0,0$, $0,1,0,0,1,1,1,0,0$ and $0,1,1,1,0,1,0,1,1$ for Documents 1 to 3.

    Step 1, text normalisation: the documents are put in lower case and split into tokens, with no stop word removed for so small a corpus. Step 2, the dictionary holds nine words: sahil, likes, to, play, cricket, sajal, too, also, basketball. Step 3, each document's words are counted into a vector. Step 4, the three vectors form the document vector table below, which is the output.

    Step-by-step solution →
12. Q52 CBSE 2022
    With ​reference to NLP, explain the following terms in detail ​with ​the help ​of suitable ​example : Term ​frequency Inverse ​Document Frequency
    Show answer

    TF is a word's frequency in one document; IDF is total documents divided by documents containing the word; TFIDF gives rare words high value.

    Term frequency is the frequency of a word in one document; it is read from the document vector table (in Sajal likes cricket too, TF(cricket) = 1). Inverse document frequency is the total number of documents divided by the number of documents in which the word occurs. For the corpus Sahil likes to play cricket / Sajal likes cricket too / Sajal also likes to play basketball, likes occurs in all 3, so IDF $=\frac{3}{3}=1$, while basketball occurs in 1, so IDF $=\frac{3}{1}=3$. Together, TFIDF $=\text{TF}\times \log (\text{IDF})$ gives common words low value and rare words high value.

    Step-by-step solution →