Experts have designed these Class 10 AI Important Questions Chapter 6 Natural Language Processing Class 10 Important Questions and Answers NCERT Solutions Pdf for effective learning.
Natural Language Processing Class 10 Important Questions
Class 10 AI Natural Language Processing Important Questions
Important Questions of Natural Language Processing Class 10 – Class 10 Natural Language Processing Important Questions
Very Short Answer Type Questions (1markeach)
Question 1.
The business or project requirements for the AI model are reviewed in?
Answer:
The business and project requirements for the AI model are reviewed in Problem Scoping.
Question 2.
What is Problem Scoping?
Answer:
It is the process of identifying a problem,recognising its scope and having a vision to solve it.
Question 3.
When starting with a project what aspects should a person have clear understanding of?
Answer:
When starting a project the person should have a clear understanding of the problem statement first.
Question 4.
What is semantic ambiguity and when does it occur
Answer:
Semantic ambiguity occurs when the meaning of the words themselves can be misinterpreted.
Question 5.
What is termed as the Problem Statement Template?
Answer:
The template or framework that encapsulates the content of all the cards on the 4 Ws Problem Canvas
Short Answer Type Questions (2 marks each)
Question 1.
What is the fundamental difference between Human language and computer language?
Answer:
The funadmental difference between human language and computer language lies in their nature and processing capabilities. Human language is more complex and diverse,allowing seamless communication through speech signals and visual cues processed by the brain. In contrast computers understand only binary language and lack the ability to perceive errors in the input unlike humans.
Question 2.
What is meant by a dictionary in NLP?
Answer:
Dictionary in NLP means a list of all the unique words occurring in the corpus. If some words are repeated in different documents, they are all written just once in a while creating the dictionary.
Question 3.
What are the types of data used for Natural Language Processing applications?
Answer:
Natural Language Processing takes in the data of Natural Languages in the form of written words and spoken words which humans use in their daily lives and operate on this.
Question 4.
Mention some applications of Natural Language Processing.
Answer:
Natural Language Processing Applications-
- Sentiment Analysis.
- Chatbots & Virtual Assistants.
- Text Classification.
- Text Extraction.
- Machine Translation
- Text Summarisation
- Market Intelligence
- Auto-Correct
Question 5.
Give an example of the following:
(a) Multiple meanings of a word
(b) Perfect syntax, no meaning
Answer:
(a) Example of Multiple meanings of a word: His face turns red after consuming the medicine Meaning Is he having an allergic reaction? Or is he not able to bear the taste of that medicine?
(b) Example of Perfect syntax, no meaning: Chickens feed extravagantly while the moon drinks tea. This statement is correct grammatically but it does not make any sense. In Human language, a perfect balance of syntax and semantics is important for better understanding.
Question 6.
What do you mean by document vectors?
Answer:
Document Vector contains the frequency of each word of the vocabulary in a particular document. In the document, vector vocabulary is written in the top row. Now, for each word ih the document, if it matches the vocabulary, put a 1 under it. If the same word appears again, increment the previous value by 1 . And if the word does not occur in that document, put a 0 under it.
Question 7.
Which words in a corpus have the highest values and which ones have the least?
Answer:
Stop words like and, this, is, the, etc. have the highest values in a corpus. But these words do not talk about the corpus at all. Hence, these are termed as stopwords and are mostly removed at the preprocessing stage only.
Rare or valuable words occur the least but add the most important to the corpus. Hence, when we look at the text, we take frequent and rare words into consideration.
Question 8.
What is the significance of converting the text into a common case?
Answer:
In Text Normalisation, we undergo several steps to normalise the text to a lower level. After the removal of stop words, we convert the whole text into a similar case, preferably lower case.
This ensures that the case sensitivity of the machine does not consider the same words as different just because of different cases.
Question 9.
What are stop words? Explain with the help of examples.
Answer:
“Stop words” are the most common words in a language like “the”, “a”, “on”, “is”, “all”. These words do not carry important meanings and are usually removed from texts.
It is possible to remove stop words using Natural Language Toolkit (NLTK), a suite of libraries and programs for symbolic and statistical natural language processing.
Question 10.
What is Cognitive Behavioural Therapy (CBT)?
Answer:
One of the most effective ways to deal with stress. is cognitive behavioural therapy (CBT), which is popular since it is simple to apply to people and produces positive outcomes. Understanding a person’s behaviour and mentality in daily life is part of this therapy. Therapists assist clients in overcoming stress and leading happy lives with the aid of CBT.
Question 11.
What is Problem Scoping?
Answer:
Understanding a problem and identifying numerous elements that have an impact on it help define the project’s purpose or objective. Who, What, Where, and Why are the 4 Ws of problem scoping. These Ws make it easier and more effective to identify and understand the problem.
Question 12.
What is Data Acquisition?
Answer:
We need to gather conversational data from people in order to decipher their statements and comprehend their meaning in order to grasp their feelings. This collection of information is known as Data Acquistion. Such information can be gathered in a variety of ways.
- Surveys
- Observing the therapist’s sessions
- Databased available on the internet
Question 13.
What is Data Exploration?
Answer:
Once the textual information has been gathered using Data Acquistition, it must be cleaned up and processed before being delivered to the machine in a simpler form. As a result, the text is normalised using a number of processes, and the vocabulary is reduced to a minimum because the computer just needs the text’s main ideas rather than its grammar.
Question 14.
What is Data Modelling?
Answer:
After the text has been normalised, an NLP-based Al model is then fed the data. Keep in mind that in NLP, data pre-processing is only necessary after which the data is supplied to the computer. There are numerous Al models that can be used, depending on the kind of chatbot we’re trying to create, to help us lay the groundwork for our project.
Question 15.
What is Data Evaluation?
Answer:
The correctness of the trained model is determined based on how well the machine-generated answers match the user’s input is knwon as Data Evaluation. The chatbot’s proposed answers are contrasted with the correct answers to determine the model’s efficacy.
Question 16.
What do you mean by Multiple Meanings of a word in Deep Learning?
Answer:
Depending on the context, the term mouse can be used to refer to either a mammal or a computer device. Consequently, mouse is described as ambiguous. The Principle of Economical Versatility of Words states that common words have a tendency to acquire additional senses, which can create practical issues in subsequent jobs.
Additionally, this meaning conflation has additional detrimental effects on correct semantic modelling, such as the pulling together in the semantic space of words that are semantically unrelated yet are comparable to distinct meanings of the same word.
Question 17.
What is Data Processing?
Answer:
Making data more meaningful and informative is the effort of changing it from a given form to one that is considerably more useable and desired. This entire process can be automated using Machine Learning algorithms, mathematical modelling, and statistical expertise.
Question 18.
What is Text Normalisation?
Answer:
The process of converting a text into a canonical (standard) form is known as text normalisation. For instance, the canonical form of the word “good” can be created from the words “gooood” and “gud.” Another case is the reduction of terms that are nearly identical, such as “stopwords,” “stopwords,” and “stop words,” to just “stopwords.”
We must be aware that we will be working on a collection of written text in this portion before we start. As a result, we will be analysing text from a variety of papers. This collection of text from all the documents is referred to as a corpus. We would perform each stage of Text Normalisation and test them on a corpus in addition to going through them’all.
Question 19.
What is Sentence Segmentation in Al?
Answer:
The challenge of breaking down a string of written language into its individual sentences is known as sentence segmentation. The method used in NLP to determine where sentences actually begin and end, or you can just say that this is how we divide a text into sentences. Sentence segmentation is the process in question. Using the spacy library, we implement this portion of NLP in Python.
Question 20.
What is Tokenisation in AI?
Answer:
The challenge of breaking down a string of written language into its individual words is known as word tokenisation (also known as word segmentation). Space is a good approximation of a word divider in English and many other languages that use some variation of the Latin alphabet.
Question 21.
What is purpose of Stopwords?
Answer:
Stopwords are words that are used frequently in a corpus but provide nothing useful. Humans utilise grammar to make their sentences clear and understandable for the other person. However, grammatical terms fall under the category of stopwords because they do not add any significance to the information that is to be communicated through the statement. Stopword examples include: a/ an/ and/ are/ as/ for/ it/ is/ into/ in/if/ on/ or/ such/ the/ there/ to
Question 22.
What is Stemming in AI?
Answer:
The act of stripping words of their affixes and returning them to their original forms is known as stemming. The process of stemming can be carried out manually or by an algorithm that an AI system may use. Any inflected form that is encountered can be reduced to its root by using a variety of stemming techniques. A stemming algorithm can be created easily.
Question 23.
What is Lemmatisation?
Answer:
Stemming and lemmatisation are alternate techniques to one another because they both function to remove affixes. However, lemmatisation differs from both of them in that the word that results from the elimination of the affix (also known as the lemma) is meaningful.
Lemmatisation takes more time to complete than stemming because it ensures that the lemma is a word with meaning.
Question 24.
What is bag of Words?
Answer:
Bag of Words is a model for natural language processing that aids in removing textual elements that can be used by machine learning techniques. We obtain each word’s occurrences from the bag of words and create the corpus’s vocabulary.
An approach to extracting features from text for use in modelling, such as with machine learning techniques, is known as a bag-of-words model, or BoW for short. The method is really straightforward and adaptable, and it may be applied in a variety of ways to extract features from documents.
Question 25.
What is TFIDF?
Answer:
TF-IDF, which stands for term frequency-inverse document frequency, is a metric that is employed in the fields of information retrieval (IR) and machine learning to quantify the significance or relevance of string representations (words, phrases, lemmas, etc.) in a document among a group of documents (also known as a corpus).
Long Answer Type Questions (4 marks each)
Question 1.
What is inverse document frequency?
Answer:
To understand inverse document frequency, first, we need to understand document frequency.
Document Frequency is the number of documents in which the word occurs irrespective of how many times it has occurred in those documents.
In the case of inverse document frequency, we need to put the document frequency in the denominator while the total number of documents is the numerator. For example, if the document frequency of the word “AMAN” is 2 in a particular document then its inverse document frequency will be 3 / 2. (Here no. of documents is 3)
Question 2.
Define the following:
(i) Stemming
(ii) Lemmatisation?
Answer:
Stemming is a technique used to extract the base form of the words by removing affixes from them. It is just like cutting down the branches of a tree to its stems.
For example, the stem of the words eating, eats, eaten is eaten.
Lemmatisation is the grouping together of different forms of the same word. In search queries, lemmatisation allows end-users to query any version of a base word and get relevant results.
Question 3.
Does the vocabulary of a corpus remain the same before and after text normalisation? Why?
Answer:
No, the vocabulary of a corpus does not remain the same before and after the text normalisation. Reasons are:
- In normalisation, the text is normalised through various steps and is lowered to minimum vocabulary since the machine does not require grammatically correct statements but the essence of it.
- In normalisation Stop words, Special Characters and Numbers are removed.
- In stemming the affixes of words are removed and the words are converted to their base form.
- So, after normalisation, we get a reduced vocabulary.
Question 4.
Explain the concept of Bag of Words.
Answer:
Bag of Words is a Natural Language Processing model which helps in extracting features out of the text which can be helpful in machine learning algorithms.
In a bag of words, we get the occurrences of each word and construct the vocabulary for the corpus.
Bag of Words just creates a set of vectors containing the count of word occurrences in the document (reviews). Bag of Words vectors is easy to interpret.
Explain how AI can play a role in \}entiment analysis of human beings?
The goal of sentiment analysis is toidentify sentiment among several posts or even in the same post where emotion is not always explicitly expressed.
Companies use Natural Language Processing applications, such as sentiment analysis, to identify opinions and sentiments online to help them understand what customers think about their products and services (i.e., “I love the new iPhone” and, a few lines later “But sometimes it doesn’t work well” where the person is still talking about the iPhone) and overall.
Beyond determining simple polarity, sentiment analysis understands sentiment in context to help better understand what’s behind an expressed opinion, which can be extremely relevant in understanding and driving purchasing decisions.
Question 5.
What are the steps of text Normalisation? Explain them in brief.
Answer:
In, Text Normalisation we undergo several steps to normalise the text to a lower level.
(a) Sentence Segmentation:
Under sentence segmentation, the whole corpus is divided into sentences. Each sentence is taken as a different data so now the whole corpus gets reduced to sentences.
(b) Tokenisation:
After segmenting the sentences, each sentence is then further divided into tokens.
A token is a term used for any word or number or special character occurring in a sentence.
Under tokenisation, every word, number, and special character is considered separately and each of them is now a separate token.
(c) Removing Stop words, Special Characters, and Numbers:
In this step, the tokens which are not necessary are removed from the token list.
(d) Converting text to a common case:
After the stop words removal, we convert the whole text into a similar case, preferably lower case. This ensures that the case sensitivity of the machine does not consider the same words as different just because of different cases.
(e) Stemming
In this step, the remaining words are reduced to their root words. In other words, stemming is the process in which the affixes of words are removed and the words are converted to their base form.
(f) Lemmatisation
In lemmatisation, the word we get after affix removal (also known as lemma) is a meaningful one.
With this, we have normalised our text to tokens which are the simplest form of words present in the corpus.
Now it is time to convert the tokens into numbers. For this, we would use the Bag of Words algorithm.
Question 6.
What is the need of text normalisation in NLP?
Answer:
- Since we all know that the language of computers is Numerical, the very first step that comes to our mind is to convert our language to numbers. This conversion takes a few steps to happen.
- The first step to it is Text Normalisation. Since human languages are complex, we need to, first of all, simplify them in order to make sure that understanding becomes possible.
- Text Normalisation helps in cleaning up the textual data in such a way that it comes down to a level where its complexity is lower than the actual data.
Question 7.
What are the applications of TFIDF?
Answer:
TFIDF is commonly used in the Natural Language Processing domain. Some of its applications are:
- Document Classification: Helps in classifying the type and genre of a document.
- Topic Modelling: It helps in predicting the tepic for a corpus.
- Information Retrieval System: To extract the important information out of a corpus.
- Stop word filtering: This helps in removing unnecessary words from a text body.
Question 8.
What are the different applications of NLP which are used in real-life scenario?
Answer:
Some of the applications which is used in the reallife scenario are:
Automatic Summarisation: Automatic summarisation is useful for gathering data from social media and other online sources, as well as for summarising the meaning of documents and other written materials. When utilised to give a summary of a news story or blog post while eliminating redundancy from different sources and enhancing the diversity of content acquired, automatic summarising is particularly pertinent.
Sentiment Analysis: In posts when emotion is not always directly expressed, or even in the same post, the aim of sentiment analysis is to detect sentiment. To better comprehend what internet users are saying about a company’s goods and services, businesses employ natural language processing tools like sentiment analysis.
Text Classification: Text classification enables you to classify a document and organise it to make it easier to find the information you need or to carry out certain tasks. Spam screening in email is one example of how text categorisation is used.
Virtual Assistants: These days, digital assistants like Google Assistant, Cortana, Siri, and Alexa play a significant role in our lives. Not only can we communicate with them, but they can also facilitate our life. They can assist us in ṃaking notes about our responsibilities, making calls for us, sending messages, and much more by having access to our data.
Question 9.
What is a Chatbot?Where are they used? Give a few examples.
Answer:
A chatbot is a piece of software or an agent with artificial intelligence that uses natural language processing to mimic a conversation with users or people. You can have the chat through a website, application, or messaging app. These chatbots, often known as digital assistants, can communicate with people verbally or via text.
The majority of organisations utilise AI chatbots, such the Vainubot and HDFC Eva chatbots, to give their clients virtual customer assistance around-the-clock.
Some of the example of Chatbot:
- Mitsuku Bot
- CleverBot
- Jabberwacky
- Haptik
- Rose
- Ochtbot
- chatgpt
Question 10.
Reframe: What are the different types of chatbots? Explain.
Answer:
There are two types of Chatbot –
(a) Script Bot: An Internet bot, sometimes known as a web robot, robot, or simply bot, is a software programme that does automated operations (scripts) over the Internet, typically with the aim of simulating extensive human online activity like communicating.
(b) Smart Bot: An artificial intelligence (AI) system that can learn from its surroundings and past experiences and develop new skills based on that knowledge is referred to as a smart bot. Smart bot that are intelligent enough can operate alongside people and learn from their actions.
Question 11.
Difference between human language vs computer language?
Answer:
Although there is a significant difference between* the languages, human language and computer language can be translated into one other very flawlessly. Human languages can be used in voice, writing, and gesture, whereas machinebased languages can only be used in written communication. A computer’s textual language can communicate with vocal or visual clues depending on the situation, as in AI chatbots with procedural animation and speech synthesis. But in the end, language is still written. The languages also have different meanings. Human languages are utilised in a variety of circumstances, including this blog post, whereas machine languages are almost solely used for requests, commands, and logic.
Question 12.
What are the different applications of TFIDF?
Answer:
TFIDF is commonly used in the Natural Language Processing domain. Some of its applications are:
Document classification: Helps in classifying the type and genre of a document.
Topic Modelling: It helps in predicting the topic for a corpus.
Information Retrieval System: To extract the important information out of a corpus.
Stop word filtering: Helps in removing the unnecessary words out of a text body.
Question 13.
Write the steps necessary to implement the bag of words algorithm.
Answer:
The steps to implement bag of words algorithm are as follows:
(a) Text Normalisation: Collect data and pre-process it.
(b) Create Dictionary: Make a list of all the unique words occurring in the corpus.
(c) Create document vectors: For each document in the corpus, find out how many times the word from the unique list of words has occurred.
(d) Create document vectors for all the documents.
Case Based Subjective Questions:
I. Read the following text and answer the following questions based on the same:
Natufal Language Processing (NLP) is a field of artificial intelligence (AI) that focuses on the interaction between computers and humans through natural language. Its primary goal is to enable computers to understand, interpret, and generate human language in a way that is both meaningful and useful.
NLP encompasses a wide range of tasks and techniques, including:
(i) Text Understanding: This involves tasks such as parsing, semantic analysis, and named entity recognition, which aim to extract meaning from text.
(ii) Text Generation: This includes tasks such as machine translation, summarisation, and dialogue generation, where the goal is to produce humanlike text based on input from various sources.
(iii) Text Classification: This involves categorising text into predefined categories or labels, such as sentiment analysis, spam detection, and topic classification.
(iv) Information Extraction: This involves extracting structured information from unstructured text, such as extracting entities, relationships, and events from news articles or documents.
(v) Language Modeling: This involves building statistical or neural network-based models of language, which can be used for tasks such as autocomplete, spell checking, and language generation.
NLP techniques often rely on machine learning and deep learning algorithms to process and analyse large amounts of text data. These algorithms learn patterns and relationships from data and can be trained to perform specific NLP tasks.
NLP has numerous real-world applications across various domains, including:
Virtual Assistants: NLP powers virtual assistants like Siri, Alexa, and Google Assistant, enabling users to interact with devices using natural language commands.
Sentiment Analysis: NLP can be used to analyse social media posts, customer reviews, and feedback to determine sentiment and gauge public opinion.
Language Translation: NLP enables automatic translation of text between different languages, facilitating communication across linguistic barriers.
Information Retrieval: NLP techniques are used in search engines to understand user queries and retrieve relevant documents or web pages.
Healthcare: NLP is used in medical research and healthcare applications for tasks such as extracting information from electronic health records, analysing clinical notes, and assisting in diagnosis and treatment. Overall, NLP plays a crucial role in bridging the gap between human language and computer understanding, enabling a wide range of applications that enhance communication, information retrieval, and decision-making processes.
Question 1.
What is the primary goal of NLP?
Answer:
NLP’s primary goal is to enable computers to understand, interpret, and generate human language in a way that is both meaningful and useful
Question 2.
Name some tasks and techniques of NLP.
Answer:
NLP encompasses a wide range of tasks and techniques:
Text Understanding, Text Generation, Text Classification, Information Extraction and Language Modeling.
Question 3.
What do you mean by Virtual Assistants?
Answer:
NLP powers virtual assistants like Siri, Alexa, and Google Assistant, enabling users to interact with devices using natural language commands.
Question 4.
What is the use of NLP in healthcare?
Answer:
NLP is used in medical research and healthcare applications for tasks such as extracting information from electronic health records, analysing clinical notes, and assisting in diagnosis and treatment.