Q1. What do you mean by Natural Language Processing?

Answer 1– The area of artificial intelligence known as natural language processing,

or NLP, is dedicated to making it possible for computers to comprehend and process
human languages. The interaction between computers and human (natural)
languages is the focus of artificial intelligence (AI), a subfield of linguistics, computer
science, information engineering, and artificial intelligence. This includes learning
how to programme computers to process and analyze large amounts of natural
language data.
Q2. What are the different applications of NLP which are used in real-life
scenario?
Answer 2 – Some of the applications which is used in the real-life scenario are –
a. Automatic Summarization – Automatic summarization is useful for gathering
data from social media and other online sources, as well as for summarizing the
meaning of documents and other written materials. When utilized 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 summarizing is particularly
pertinent.
b. 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.
c. Text Classification – Text classification enables you to classify a document and
organize 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 categorization is used.
d. 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
making notes about our responsibilities, making calls for us, sending messages, and
much more by having access to our data.
e. Chatbot -A chatbot is a computer program that's designed to simulate human
conversation through voice commands or text chats or both. Eg: Mitsuku Bot,
Jabberwacky etc.

Q3. How NLP is used in healthcare?

Ans 3.An advanced NLP algorithm can interpret and extract disease conditions such
as speech disorders , mental fatigue and distress from the words spoken by the
patient. The health records I digital form can be processed by NLP application for
predicting fatal disease.

Q4. What is Cognitive Behavioural Therapy (CBT)?

Answer 4– 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.
Q5. How data can be collected?
Ans. 5 a. Surveys
b. Observing the therapist’s sessions
c. Interview

Q6. What is Chatbot?

Answer 6 – 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 organizations utilize 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 –

a. Mitsuku Bot
b. CleverBot
c. Jabberwacky
d. Haptik
e. Rose
f. Ochtbot

Q7. Types of Chatbot?

Answer7 – 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.

Q8. Name the two chatbots developed by British Programmer Rollo Carpenter.
Ans 8. The two chatbots developed by British Programmer Rollo Carpenter are.
1) Cleverbot
2) Jabberwacky

Q9. Difference between human language vs computer language?

Answer 9 – 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 machine-
based 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 utilized in a variety of circumstances, including this blog post,
whereas machine languages are almost solely used for requests, commands, and
logic.

Q10. Differentiate between Syntax V/s. Semantics.

Ans 10. syntax refers to grammar, while semantics refers to meaning.
Syntax is the set of rules needed to ensure a sentence is grammatically
correct; semantics is how one's lexicon, grammatical structure, tone, and
other elements of a sentence coalesce to communicate its meaning.

Q11. What do you mean by Multiple Meanings of a word in Deep Learning?

Answer 11 – 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.

Q12. What is Data Processing?

Answer 12– 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.

Q13. What is Text Normalisation?

Answer 13– 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 “good” and “gud.” Another case is the reduction of terms
that are nearly identical, such as “stop words,” “stop-words,” 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 Normalization and test them on a corpus in addition to
going through them all.

Q14. Why is text normalization important?

Ans 14- While text normalization we reduce the randomness and bring them closer to
predefined standards. It reduces the amount of different information that the
computer has to deal with and therefore improves efficiency.

Corpus
• The text and terms collected from various documents and used for whole
textual data from all documents altogether is known as corpus.
• To work out on corpus these steps are required:
a. Sentence Segmentation
• Sentence segmentation divides the corpus into sentences.
• Each sentence is taken as a different data so now the corpus gets reduced to
sentences.

b. Tokenisation
• After sentence segmentation, each sentence is further divided into tokens.
• The 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 Stopwords, Special Characters and Numbers

• Stop words are those words that are used very frequently in the corpus and do
not add any value to the corpus.
 • In human language, there are certain words used to grammar which does not
add any essence to the corpus.
• Some examples of stop words are:

The above words have little or no meaning in the corpus, hence these words are
removed and focused on meaningful terms.

Along with these stopwords, the corpus may have some special characters and
numbers. Sometimes some of them are meaningful, sometimes not. For example, for
email ids, the symbol @ and some numbers are very important. If symbolism special
characters and numbers are not meaningful can be removed like stopwords.

Converting text to a common case

• The next step after removing stopwords, convert the whole text into a similar
case.
• The most preferable case is the lower case.
• This ensures that the case sensitivity of the machine does not consider the
same words as different just because of different cases.

In the above example, the word “hello” is written in 6 different forms, which are
converted into lower case and hence all of them are treated as a similar word by the
machine.

d. Stemming
• In this step, the words are reduced to their root words.
 • Stemming is the process in which the affixes of words are removed and the
words are converted to their base form.
• Note that in stemming, the stemmed words (words which we get after
removing the affixes) might not be meaningful.
• Here in this example as you can see: healed, healing and healer all were
reduced to heal but studies were reduced to studi after the affix removal which
is not a meaningful word.
• Stemming does not take into account if the stemmed word is meaningful or
not.
• It just removes the affixes hence it is faster.

Word Affix Stem

healed ed heal

healing ing heal

healer er heal

studies es studi

studying ing study

• In stemming, the stemmed words are not meaningful always.

• As you can observe in the above table healed, healing, healer reduced to heal
and studies reduced to studi.
• Stemming does not take into account if the stemmed word is meaningful or
not.
• It just removes the affixes hence it is faster.

In the next section of Unit 6 Natural Language Processing AI Class 10 we are going
to discuss lemmatization. Here we go!

e. Lemmatization
• It is an alternate process of stemming.
• It also removes the affix from the corpus.
• The only difference between lemmatization and stemming is the output of
lemmatization are meaningful words.
• The final output is known as a lemma.
• It takes a longer time to execute than stemming.
• The following table shows the process.
 Word Affix Stem

healed ed heal

healing ing heal

healer er heal

studies es study

studying ing study

Compare the tables of stemming and lemmatization table, you will find the word
studies converted into studi by stemming whereas the lemma word is study.

Observe the following example to understand stemming and lemmatization:

After normalisation of the corpus, let’s convert the tokens into numbers. To do so
the bag of words algorithm will be used.