1
00:00:00,000 --> 00:00:00,000
Hello guys.

2
00:00:00,000 --> 00:00:03,000
So we are going to continue the discussion with respect to NLP.

3
00:00:03,000 --> 00:00:10,000
And in this video we are going to discuss about some of the amazing use cases and these use cases.

4
00:00:10,000 --> 00:00:13,000
We use it every day in our day to day activities.

5
00:00:13,000 --> 00:00:14,000
Right.

6
00:00:14,000 --> 00:00:19,000
So let me go ahead and let me share my screen and let me talk about every use cases.

7
00:00:19,000 --> 00:00:20,000
One by one will be discussing about it.

8
00:00:20,000 --> 00:00:24,000
And this will give you a clear idea about what is natural language processing.

9
00:00:24,000 --> 00:00:27,000
Now here I have opened my Gmail tab.

10
00:00:27,000 --> 00:00:32,000
Now in this specific Gmail you will be able to see that, uh, let's say that I really want to write

11
00:00:32,000 --> 00:00:33,000
some email, right?

12
00:00:33,000 --> 00:00:35,000
So I'll say hello, Krish.

13
00:00:36,000 --> 00:00:36,000
Okay.

14
00:00:36,000 --> 00:00:38,000
And let's say I made a spelling mistake.

15
00:00:38,000 --> 00:00:39,000
Okay.

16
00:00:39,000 --> 00:00:44,000
I wanted to clarify.

17
00:00:44,000 --> 00:00:46,000
So I have actually written a wrong spelling.

18
00:00:46,000 --> 00:00:51,000
So here you can see that automatically the spelling has been corrected.

19
00:00:51,000 --> 00:00:51,000
Right.

20
00:00:51,000 --> 00:00:53,000
And this is all because of NLP.

21
00:00:53,000 --> 00:00:58,000
And in this also we can like suppose if we receive an email from someone, right, we can also write

22
00:00:58,000 --> 00:00:59,000
an automated email from them.

23
00:00:59,000 --> 00:01:05,000
So that basically means it will basically tell us that what kind of text it will auto generate and it

24
00:01:05,000 --> 00:01:07,000
will give it for us, and we can actually send it.

25
00:01:07,000 --> 00:01:16,000
So I would like to I wanted to clarify about the data science and let's say I'll write course.

26
00:01:16,000 --> 00:01:17,000
Okay.

27
00:01:17,000 --> 00:01:19,000
Now let's see what it basically gives.

28
00:01:19,000 --> 00:01:21,000
It can also give you a suggestion like this.

29
00:01:21,000 --> 00:01:23,000
And now you can basically select the course right.

30
00:01:23,000 --> 00:01:25,000
So this is also one amazing use cases.

31
00:01:25,000 --> 00:01:27,000
And we use it every day.

32
00:01:27,000 --> 00:01:29,000
Now let's say I go to my LinkedIn.

33
00:01:29,000 --> 00:01:32,000
So here uh Rudra Pratap Singh is one of my student.

34
00:01:32,000 --> 00:01:38,000
And automatically we can see that two tags automated replies there in the LinkedIn itself.

35
00:01:38,000 --> 00:01:43,000
And this is also an amazing application from NLP, so that if you really want to just provide this,

36
00:01:43,000 --> 00:01:47,000
any of this particular two tag, you can just click it and you can reply back.

37
00:01:47,000 --> 00:01:50,000
So in this, in short, is saving you a lot of time.

38
00:01:50,000 --> 00:01:55,000
Now similarly, if I go with respect to one more application that is Google Translate, and I hope everybody

39
00:01:55,000 --> 00:01:59,000
uses this, let's say that I just go ahead and write one language.

40
00:01:59,000 --> 00:02:03,000
I'll just say, how are you?

41
00:02:03,000 --> 00:02:03,000
Right.

42
00:02:03,000 --> 00:02:07,000
And I probably want to convert this into Arabic or no.

43
00:02:07,000 --> 00:02:07,000
Okay.

44
00:02:07,000 --> 00:02:10,000
So it looks something like this with this specific language.

45
00:02:10,000 --> 00:02:12,000
Suppose if I really want to convert this into Hindi.

46
00:02:12,000 --> 00:02:18,000
So then you can basically say that automatically the text is coming like here right?

47
00:02:18,000 --> 00:02:21,000
In Hindi we basically say kya haal for how are you.

48
00:02:21,000 --> 00:02:24,000
So this is also happening because of NLP.

49
00:02:24,000 --> 00:02:25,000
Amazing application.

50
00:02:26,000 --> 00:02:29,000
And we use this and in most of the websites also, right.

51
00:02:29,000 --> 00:02:34,000
Let's say in LinkedIn, if somebody is posting in some different language below, only you will get

52
00:02:34,000 --> 00:02:37,000
an option of something called a C translation.

53
00:02:37,000 --> 00:02:41,000
So once you click that particular thing and automatically gets converted to English.

54
00:02:41,000 --> 00:02:44,000
Not only that guys, let's say that I'm just going to go ahead and search for Krishna.

55
00:02:45,000 --> 00:02:46,000
So Krishna is my name.

56
00:02:46,000 --> 00:02:47,000
I'm a YouTuber.

57
00:02:47,000 --> 00:02:49,000
I'm also a co-founder of inherent AI.

58
00:02:49,000 --> 00:02:54,000
But here if I probably go and collect on select on images.

59
00:02:54,000 --> 00:03:00,000
Now here you can see that it is already been able to detect my image and it is in turn converting that

60
00:03:00,000 --> 00:03:02,000
the text into images.

61
00:03:02,000 --> 00:03:08,000
It is understanding the text and it is basically thinking okay, it knows that it is talking about myself

62
00:03:08,000 --> 00:03:09,000
and based on the web, right?

63
00:03:09,000 --> 00:03:12,000
It is being able to capture all the images that is available in the web.

64
00:03:12,000 --> 00:03:14,000
So this is also an amazing thing.

65
00:03:14,000 --> 00:03:17,000
And probably if I probably go ahead and select videos here.

66
00:03:17,000 --> 00:03:23,000
Also, you'll be able to see all the videos of my in my YouTube channel, or probably in all the other

67
00:03:23,000 --> 00:03:26,000
public platform that I have, which is being accessible over a web.

68
00:03:26,000 --> 00:03:28,000
So this is an also amazing example.

69
00:03:28,000 --> 00:03:30,000
Text to image, text to video.

70
00:03:30,000 --> 00:03:34,000
And a lot of research is also currently going on with respect to different different companies.

71
00:03:34,000 --> 00:03:39,000
There is an amazing company which is called as hugging face and hugging face have actually created an

72
00:03:39,000 --> 00:03:44,000
amazing models and solutions for solving question answering session question answering.

73
00:03:44,000 --> 00:03:49,000
It has basically question answering model, some summarization, text classification, translation.

74
00:03:49,000 --> 00:03:50,000
Right.

75
00:03:50,000 --> 00:03:51,000
All these particular use cases are there.

76
00:03:51,000 --> 00:03:56,000
And you can see that how many different kind of models it has like for question answering.

77
00:03:56,000 --> 00:03:56,000
Right.

78
00:03:56,000 --> 00:03:59,000
It has 2380 models summarization.

79
00:03:59,000 --> 00:04:03,000
It has five, eight, eight models uh for text classification as it has this much models.

80
00:04:03,000 --> 00:04:03,000
Right.

81
00:04:03,000 --> 00:04:08,000
And here you can see that how many companies are basically using this Google AI, Intel spin bridge.

82
00:04:08,000 --> 00:04:10,000
Bob Microsoft, Grammarly.

83
00:04:10,000 --> 00:04:10,000
Right.

84
00:04:10,000 --> 00:04:12,000
All these things are basically using this.

85
00:04:13,000 --> 00:04:17,000
Uh, and again, this is an amazing application of NLP itself because all these applications are, in

86
00:04:17,000 --> 00:04:22,000
short, taking the text data only and performing different kind of tasks on top of it.

87
00:04:22,000 --> 00:04:27,000
So one more amazing thing that I really want to show you as an application with respect to Alexa and

88
00:04:27,000 --> 00:04:28,000
Google Assistant.

89
00:04:28,000 --> 00:04:31,000
Uh, I have some of the Alexa home configured over here.

90
00:04:31,000 --> 00:04:35,000
I can control my ACS and lights, but with respect to Google Assistant, a simple application, I can

91
00:04:35,000 --> 00:04:36,000
go and open it.

92
00:04:36,000 --> 00:04:38,000
So here I have my Google Assistant.

93
00:04:38,000 --> 00:04:43,000
Now here you can see that hey Google, do I have any doctor appointments tomorrow?

94
00:04:45,000 --> 00:04:49,000
Sorry, I can't find anything on your calendar that matches that.

95
00:04:49,000 --> 00:04:53,000
So now here you can see that, uh, already it is being able to retrieve from my calendar.

96
00:04:53,000 --> 00:04:56,000
It is able to see whether I have a doctor appointment or not tomorrow.

97
00:04:56,000 --> 00:05:03,000
So this way it is really, really easy finding all the tasks with respect to most of the critical things

98
00:05:03,000 --> 00:05:05,000
right that we do in our day to day activities.

99
00:05:05,000 --> 00:05:10,000
So we use extensively NLP a lot in our day to day activities.

100
00:05:10,000 --> 00:05:14,000
And uh, this is what we are going to learn in this specific course, how we can build this kind of

101
00:05:14,000 --> 00:05:17,000
models, what kind of text pre-processing actually happens.

102
00:05:17,000 --> 00:05:21,000
We'll get a crux idea behind it, how these applications also works.

103
00:05:21,000 --> 00:05:21,000
Okay.

104
00:05:21,000 --> 00:05:26,000
So yes, uh, this was about the second video of mine, uh, with respect to natural language processing

105
00:05:26,000 --> 00:05:27,000
and machine learning.

106
00:05:27,000 --> 00:05:31,000
I will see you all in the next video where we are going to start the syllabus.

107
00:05:31,000 --> 00:05:32,000
I will see you all in the next video.

108
00:05:32,000 --> 00:05:32,000
Bye bye.

109
00:05:32,000 --> 00:05:33,000
Take care.