DIYA ACADEMY OF LEARNING

Affiliated to CBSE Board, New Delhi

Affiliation No. 830420

Artificial Intelligence
Code-417
Grade 10

Bringing Education & Values Together

Natural Language Processing
• Natural Language Processing, or NLP, is the sub-field of AI that is
focused on enabling computers to understand and process human
languages.
• How do computers do that? How do they understand what we say in
our language?
• Identify the mystery animal: http://bit.ly/iai4yma
Lets Introspect
• What according to you was the task of the machine?
• Were there any challenges that you faced while playing this game? If
yes, list them down.
• What approach must one follow to win this game?
Applications of NLP
• Text classification
• To assign predefined categories to a document and organize it to help you find
the information you need or simplify some activities.
• An application of text categorization is spam filtering in email.
• Virtual Assistants
• Google Assistant, Cortana, Siri, Alexa, etc
• By accessing our data, they can help us in keeping notes of our tasks, make
calls for us, send messages and a lot more.
• With the help of speech recognition, these assistants can not only detect our
speech but can also make sense out of it.
Applications of NLP
• Chatbots
• To understand natural language and respond appropriately
• Works at the front line of customer support.
• Machine Translation
• Automatically converts one natural language to another.
• To overcome language hurdles.
• Eg. Google Translate
Applications of NLP
• Automatic Summarization
• overview of a news item or blog post
• summarizing the meaning of documents and information,
• understand the emotional meanings within the information, such as in
collecting data from social media.

• Sentiment Analysis
• To identify opinions and sentiment online to help them understand what
customers think about their products and services and overall indicators of
their reputation
• “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
 Case Study 1-Practice
The world is competitive nowadays. People face competition in even the
tiniest tasks and are expected to give their best at every point in time. When
people are unable to meet these expectations, they get stressed and could
even go into depression. We get to hear a lot of cases where people are
depressed due to reasons like peer pressure, studies, family issues,
relationships, etc. and they eventually get into something that is bad for them
as well as for others. So, to overcome this, cognitive behavioral therapy (CBT)
is considered to be one of the best methods to address stress as it is easy to
implement on people and also gives good results. This therapy includes
understanding the behavior and mindset of a person in their normal life. With
the help of CBT, therapists help people overcome their stress and live a happy
life.
Revisiting the AI Project Cycle
Stage1: Problem Scoping
 Case Study 2- Practice
Humans are social animals. We tend to organise and/or participate in various
kinds of social gatherings all the time. We love eating out with friends and family
because of which we can find restaurants almost everywhere and out of these,
many of the restaurants arrange for buffets to offer a variety of food items to their
customers. Be it small shops or big outlets, every restaurant prepares food in bulk
as they expect a good crowd to come and enjoy their food. But in most cases,
after the day ends, a lot of food is left which becomes unusable for the restaurant
as they do not wish to serve stale food to their customers the next day. So, every
day, they prepare food in large quantities keeping in mind the probable number of
customers walking into their outlet. But if the expectations are not met, a good
amount of food gets wasted which eventually becomes a loss for the restaurant as
they either have to dump it or give it to hungry people for free. And if this daily
loss is taken into account for a year, it becomes quite a big amount.
Stage2: Data Acquisition

• To understand the sentiments of people, we need to collect their

conversational data so the machine can interpret the words that they
use and understand their meaning.

• Such data can be collected from various means:

1. Surveys
2. Observing the therapist’s sessions
3. Databases available on the internet
4. Interviews, etc.
 Stage 3: Data Exploration
• Textual data collected needs to be processed and cleaned
• 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.

Stage 4: Data Modelling

Once the text has been normalised, it is then fed to an NLP based AI model. Depending
upon the type of chatbot we try to make, there are a lot of AI models available which
help us build the foundation of our project.

Stage 5: Evaluation
The accuracy for the same is generated on the basis of the relevance of the answers
which the machine gives to the user’s responses. To understand the efficiency of the
model, the suggested answers by the chatbot are compared to the actual answers.
Chatbots
Mitsuku Bot - https://www.pandorabots.com/mitsuku/
CleverBot - https://www.cleverbot.com/
Jabberwacky - http://www.jabberwacky.com/
Haptik - https://haptik.ai/contact-us
Rose -
http://ec2-54-215-197-164.us-west-1.compute.amazonaws.com/speech.php
Ochatbot - https://www.ometrics.com/blog/list-of-fun-chatbots/
 Lets Introspect
Chatbot Name Chat Bot
What is the purpose of this chatbot?

How •was the interaction

Which chatbot with
didtheyou
chatbot?
try? Name any one.
• What is the purpose of this chatbot?
Did the
• chat feel
How waslikethe
talking to a humanwith
interaction or a the chatbot?
robot? Why do you think so?
• Did the chat feel like talking to a human or a robot? Why do you think
so?
Do you feel that the chatbot has a certain
• Do you feel that the chatbot has a certain personality?
personality?
Which chatbot did you try? Name any
Examples
• Inklewriter
Script Bot
• Customer care section of companies
• Google Assistant
• Alexa Smart Bot
• Siri
 How Human Processes Language
Brain process sounds it hears and tries to make sense out of them. the
Brain is processing all the sounds but is prioritising the one on which our interest lies.

1. Sound reaches the brain through a long channel.

2. As a person speaks, the sound travels from his mouth and goes to the listener’s
eardrum.
3. The sound striking the eardrum is converted into neuron impulse.
4. Gets transported to the brain and processed.
5. After processing the signal, the brain gains understanding around the meaning of it.
6. If it is clear, the signal gets stored.
7. Otherwise, the listener asks for clarity to the speaker.
How Computer Understands Language
• The computer understands the language of numbers.
• Everything that is sent to the machine has to be converted to numbers.
• And while typing, if a single mistake is made, the computer throws an
error and does not process that part.
• The communications made by the machines are very basic and simple.
If we want the machine to understand our language, how should this
happen?
What are the possible difficulties a machine would face in processing
natural language?
Arrangement of the words and meaning
• Human language has nouns, verbs, adverbs, adjectives.
• A word can be a noun at one time and an adjective some other time.
• This is the issue related to the syntax of the language.
• Syntax refers to the grammatical structure of a sentence.
• When the structure is present, we can start interpreting the message.

How computer does this?

• Use the part-of-speech tagging. This allows the computer to identify the different parts of
a speech.
• Human communication is complex. There are multiple characteristics of the human
language that might be easy for a human to understand but extremely difficult for a
computer to understand.
Analogy with programming language:
Different syntax, same semantics: 2+3 = 3+2
Statements written is different, but their meanings are the same that is
5.
Different semantics, same syntax: 2/3 (Python 2.7) ≠ 2/3 (Python 3)
Statements written have the same syntax but their meanings are
different.
In Python 2.7, this statement would result in 1 while in Python 3, it
would give an output of 1.5.
Multiple Meanings of a word
His face turned red after he found out that he took the wrong bag
What does this mean? Is he feeling ashamed because he took another
person’s bag instead of his? Is he feeling angry because he did not
manage to steal the bag that he has been targeting?

The red car zoomed past his nose

Probably talking about the color of the car

His face turns red after consuming the medicine

Is he having an allergic reaction? Or is he not able to bear the taste of
that medicine?
Perfect Syntax, no Meaning
Chickens feed extravagantly while the moon drinks tea.

This statement is correct grammatically but does this make any sense?
In Human language, a perfect balance of syntax and semantics is
important for better understanding.
Natural Language-Data Processing
Text Normalisation
• Process of downsizing and simplifying the text to make it suitable for
machine processing.
• Involves
• removing unnecessary pieces from the text
• breaking down into smaller simple tokens
• Converting them into numeric form
• During text normalisation, processing is done on the text collected
from multiple documents and sources, called as corpus.
Step 1: Sentence Segmentation
• Corpus is broken into simple sentences.
• Each sentence is treated as a separate data to be processed
• Also known as sentence tokenization.
Step 2: Tokenization
• After segmentation, each
sentence is further broken
down into individual text
pieces called tokens.
• Also known as word
tokenization.
• Every word, number and
special character is
considered separately and
each of them is now a
separate token.
Step 3: Removing Stopwords, Special
Characters and Numbers
• Stopwords are the words which occur very frequently in the corpus
but do not add any value to it.
Along with these words, a lot of times our corpus might have special
characters and/or numbers. Now it depends on the type of corpus that
we are working on whether we should keep them in it or not. For
example, if you are working on a document containing email IDs, then
you might not want to remove the special characters and numbers
whereas in some other textual data if these characters do not make
sense, then you can remove them along with the stopwords.
Step 4: Converting text to a common case
Step 5: Stemming
• Stemming is the process in which the affixes of words are removed
and the words are converted to their base form or their root words.

Note that in stemming, the

stemmed words (words which
are we get after removing the
affixes) might not be meaningful.
Step 5: Lemmatization
• Stemming and lemmatization both are alternative processes to each
other -removal of affixes.
• Lemmatization is a process of stemming as well as converting the
stemmed word to their proper form so as to keep them meaningful.
• Lemma is a word with meaning and hence it takes a longer time to
execute than stemming.
Conversion of token into numbers
• Feature extraction from text done using the following algorithms:
• Bag of Words
• Term Frequency – Inverse Document Frequency
Bag of Words
• 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 bag of words, we get the occurrences of each word and construct
the vocabulary for the corpus.
The bag of words gives us two things:
1. A vocabulary of words for the corpus
2. The frequency of these words (number of times it has occurred in the whole
corpus).

Here calling this algorithm “bag” of words symbolises that the sequence of
sentences or tokens does not matter in this case as all we need are the unique words
and their frequency in it.

Step-by-step approach to implement bag of words algorithm:

3. Text Normalisation: Collect data and pre-process it
4. Create Dictionary: Make a list of all the unique words occurring in the corpus.
(Vocabulary)
5. Create document vectors: For each document in the corpus, find out how many
times the word from the unique list of words has occurred.
6. Create document vectors for all the documents.
Step 1: Collecting data and pre-processing it
Document 1: Aman and Anil are stressed
Document 2: Aman went to a therapist
Document 3: Anil went to download a health chatbot.
After text normalisation, the text becomes:
Document 1: [aman, and, anil, are, stressed]
Document 2: [aman, went, to, a, therapist]
Document 3: [anil, went, to, download, a, health, chatbot]

• Note that no tokens have been removed in the stopwords removal step. It is
because we have very little data and since the frequency of all the words is almost
the same, no word can be said to have lesser value than the other.
Step 2: Create Dictionary
• Go through all the steps and create a dictionary i.e., list down all the
words which occur in all three documents:

Note that even though some words are repeated in different documents,
they are all written just once as while creating the dictionary, we create
the list of unique words.
Step 3: Create document vector

1. For each word in the document, if it matches with the vocabulary,

put a 1 under it.
2. If the same word appears again, increment the previous value by 1.
3. And if the word does not occur in that document, put a 0 under it.
Step 4: Repeat for all documents

Document vector table

TFIDF: Term Frequency & Inverse
Document Frequency
• It is a plot of occurrence of words versus
their value.
• Stop words are mostly removed at the pre-
processing stage only.
• Frequent words mostly talk about the
document’s subject and their occurrence
is adequate in the corpus.
• Rare or valuable words occur the least but
add the most value to the corpus. rare or
valuable words. When we look at the text,
we take frequent and rare words into
consideration.
Demystify TFIDF
• TFIDF stands for Term Frequency and Inverse Document Frequency.
TFIDF helps us in identifying the value for each word.
• Term frequency is the frequency of a word in one document.
• Term frequency can easily be found from the document vector table
as in that table we mention the frequency of each word of the
vocabulary in each document.
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. The document frequency for the exemplar vocabulary
would be:
 Inverse Document Frequency

We need to put the document frequency in the denominator while the total
number of documents is the numerator
 Formula of TFIDF for any word W becomes:
TFIDF(W) = TF(W) * log( IDF(W) )

TF values are for each document while the IDF values are for the whole
corpus.
The IDF values for Aman in each row is the same and similar pattern is
followed for all the words of the vocabulary. After calculating all the values,
we get:

Since we have less amount of data, words like ‘are’ and ‘and’ also
have a high value. But as the IDF value increases, the value of that
word decreases
For example: Total Number of documents: 10
Number of documents in which ‘and’ occurs: 10
IDF(and) = 10/10 = 1
Which means: log(1) = 0. Hence, the value of ‘and’ becomes 0.
On the other hand, number of documents in which ‘pollution’ occurs: 3
IDF(pollution) = 10/3 = 3.3333…
Which means: log(3.3333) = 0.522; which shows that the word
‘pollution’ has considerable value in the corpus.
Summarising the concept, we can say that:
1. Words that occur in all the documents with high term frequencies
have the least values and are considered to be the stopwords.
2. For a word to have high TFIDF value, the word needs to have a high
term frequency but less document frequency which shows that the
word is important for one document but is not a common word for
all documents.
3. These values help the computer understand which words are to be
considered while processing the natural language. The higher the
value, the more important the word is for a given corpus.
Applications of TFIDF
• Document Classification Helps in classifying the type and genre of a
document.
• Topic Modelling Information: It helps in predicting the topic for a
corpus.
• 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.
 Lets Practice
Here is a corpus for you to challenge yourself with the given tasks. Use
the knowledge you have gained in the above sections and try
completing the whole exercise by yourself.
The Corpus
Document 1: We can use health chatbots for treating stress.
Document 2: We can use NLP to create chatbots and we will be making
health chatbots now!
Document 3: Health Chatbots cannot replace human counsellors now.
Accomplish the following challenges on the basis of the corpus given above. You
can use the tools available online for these challenges. Link for each tool is given
below:
1. Sentence Segmentation: https://tinyurl.com/y36hd92n
2. Tokenisation: https://textanalysisonline.com/nltk-word-tokenize
3. Stopwords removal: https://demos.datasciencedojo.com/demo/stopwords/
4. Lowercase conversion: https://caseconverter.com/
5. Stemming: http://textanalysisonline.com/nltk-porter-stemmer
6. Lemmatisation: http://textanalysisonline.com/spacy-word-lemmatize
7. Bag of Words: Create a document vector table for all documents.
8. Generate TFIDF values for all the words.
9. Find the words having highest value.
10. Find the words having the least value.
 Questions
1. What is a Chabot?
2. What is the difference between stemming and lemmatization?
3. Which package is used for Natural Language Processing in Python programming?
4. What do you mean by corpus?
5. Differentiate between a script-bot and a smart-bot.
6. What are the types of data used for Natural Language Processing applications?
7. Give an example of the following:
a. Multiple meanings of a word
b. Perfect syntax, no meaning
8. While working with NLP what is the meaning of?
a. Syntax
b. Semantics
Reference for notes
https://drive.google.com/file/d/1jhl6eribMOHmOGyXa7vCyPcZ-790wYS
2/view?usp=sharing