Natural Language Processing (NLP) is a subfield of artificial intelligence (AI) and computer science that deals with the interaction between computers and human language. The goal of NLP is to enable machines to understand, interpret, and generate human language in a way that is both natural and meaningful to humans. NLP involves a range of techniques and tools, including machine learning, deep learning, and computational linguistics, to analyze and model natural language data. These techniques allow computers to perform a wide range of language-related tasks, such as language translation, sentiment analysis, language generation, text summarization, and speech recognition. NLP has many practical applications in the real world, including in virtual assistants, chatbots, automated customer service, sentiment analysis for social media, automated translation, and content categorization. With the growth of big data and the increased need for automation, NLP is becoming increasingly important in helping businesses and organizations process and make sense of the large amounts of unstructured data they generate.

2. AGENDA
 INTRODUCTION
 THE AIM
 LANGUAGE TRANSLATION
 SPAM
 TEXT SUMMARIZATION
 AMBIGUITY SOLVING
 CONCLUSION

3. Introduction
 Natural language processing (NLP) is a field of
 Computer science
 Artificial intelligence
 Intelligence exhibited by Machines, mimics the cognitive minds
 Computational linguistics
 All about language--- kind of expertise in Natural Languages
Can we define?
 The first task is to understand the definition!!
NLP is defined as the ability of a machine (i.e. computer
program) to understand and interpret the human
language as it is spoken!
 It can be seen as an "AID provided to computers to understand
the human languages!"
 Now comes the question.
 Is it not easy to teach computers the human languages??
 Certainly not!! It is tough, daunting task!

4. Contd.,
 We are humans and we can speak the languages that we know. Be it English,
Tamil or Hindi.
 But, what a computer understands is Machine Language and is certainly not for
humans. Humans can't understand BINARY!! 0000101001010101010101 = This
could be representing Good Morning!! We can't understand.
 This is the real state of computers. But, imagine now!
 We are talking to Google Assistant, Alexa etc. We say "Alexa play the music"
and it does. Alexa, order food! It takes it up!! Ok Google, call my friend
Sachin! It calls Sachin.
 How is this possible? This interaction is made possible by NLP !! But, NLP is not
stand alone, it has Machine learning and Deep Learning Supporting it!
Process
 The user should talk to the machine.
 The machine gets the audio recorded
 The audio gets converted to Text
 The data is processed now. (here is where the machine understands your
language, NLP. ML plays handy here!)
 Then the response - AUDIO or Text comes out!! If it is a chatbot, it would be
just text reply. If it is an Audio bot, it would talk to you as well.
 For an instance, ALEXA will reply you with an answer. IRCTC chat bot will give
you text reply!

5. THE AIM
 NLP aims to get computers to perform useful tasks involving human language,
tasks like enabling human- machine communication, processing of text or
speech.
 To get the Human and Computer interaction more natural!

6. Real-time Examples.. You and I use them
all
 Google Assistant is a virtual personal assistant developed by Google allows
two way conversations. Can we test?
 OK Google! Can you tell me what's the temperature outside?
 OK Google! Can you let me know what's my name?
 OK Google! Will it rain in Coimbatore tonight?

7. LANGUAGE TRANSLATION
 This is a 100% NLP - Translation of one language to other.
 Google Translate is the most used example for you and me to understand this
better!
 Google translate is a free multilingual machine translation service developed
by Google, to translate text, speech, images, sites, or real-time video from
one language into another.

8. SPAM
 NLP helps in fighting spam. Yes, this is true.
 NLP is useful in detection of mails/messages as spam or not!.
 We shall see a demo for this in near future. (Again, with Python!)

9. TEXT SUMMARAIZATION
 The main idea of summarization is to find a subset of data which contains the
"information" of the entire set.
 Text summarization refers to the technique of shortening long pieces of text.
 The intention is to create a coherent and fluent summary having only the
main points outlined in the document. (Ignoring the unimportant content.)
 Example: I can ask you the review for a book, in a couple of lines you could
give a opinion!!

10. AMBIGUITY SOLVING
 NLP can be used here too! There could be an ambiguity!•
 One example, its handy!
o Hang him not, leave him!!!
o Hang him, not leave him!!!
 WSD (Word Sense Disambiguation)is identifying which sense of a word (i.e.
meaning) is used in a sentence, when the word has multiple meanings.
 The topics for discussion..
 Phonetics and Phonology
 Morphology
 Syntax
 Semantics
 Pragmatics
 Discourse

11. A brief note..
 Phonetics and Phonology - The study of linguistic sounds (Eg:-
Speechrecognition and Speech Synthesis)
 Morphology - The study of the meaningful components of words (Singular /
Plural)
 Syntax - The study of the structural relationships between words (ordering and
grouping of words)
 Semantics - The study of meaning
 Pragmatics - The study of how language is used to accomplish goals (what
speaker says and what listener infers)- Hang him not, leave him!!!
 Discourse - The study of linguistic units larger than a single utterance (Sachin
is a exceptional cricketer. I have seen his performances, here, his is to be
tagged as sachin)

12. LANGUAGE AMBIGUITY
 Structural Ambiguity - Different interpretation for same sentences - How
the structure of the sentence contributes to the ambiguity?
The man saw the boy with the telescope
Interpretations
1. The man [saw the boy] with the telescope
2. The man saw the [boy with the telescope]
So, it can be "Using the telescope the man saw the
boy" or "The man saw the boy,the boy had the
telescope“

13. One very interesting reference !
 I made her duck - Can we understand what all can be the different aspects
one could interpret this statement!?
 Duck - To bend, Ducking under the door to avoid get hurt. First meaning. So, I
can get a sentence as this - I asked to duck her head!
 Duck - It is waterfowl Can we make couple of sentences for this?
 I cooked Duck for her (its food here!)
 I cooked a duck, which belonged to her! (She owned it)
 I made her a duck for her to go deeper in the lake (an
amphibious transport vehicle)

14. CONCLUSION
 Utilize NLP to assist systems analysts in selecting and verifying objects and
relationships of relevance to any given project
 Save burden of analysis for system analyst
 The toolset will be intelligent enough to automatically parse, selectand relate
the objects of interest from specification documents
 Knowledge base helps in automatic generation of relevant design artifacts-
object models, data models, etc.