1 00:00:03,180 --> 00:00:05,910 Hey, welcome to today's programming concept. 2 00:00:06,600 --> 00:00:13,200 Today, I'll be talking about applications where natural language processing is used. 3 00:00:14,460 --> 00:00:21,600 That will give you a more clear understanding of what NLP natural language processing does in the real 4 00:00:21,600 --> 00:00:22,230 world. 5 00:00:22,530 --> 00:00:27,060 So one example is Google Maps reviews. 6 00:00:28,580 --> 00:00:37,070 If a user, for example, posts on Google Map a review, which is very negative, it contains hate language. 7 00:00:37,070 --> 00:00:42,630 For example, that review will be filtered out by Google Maps and it will not be displayed. 8 00:00:42,650 --> 00:00:47,780 So Google Maps would use natural language processing to detect hate language. 9 00:00:48,500 --> 00:00:53,210 That's one example of how natural language processing is used now. 10 00:00:53,600 --> 00:00:59,360 Programming language wise, what language is Google Maps using? 11 00:01:00,320 --> 00:01:07,070 That could be Python, but other languages also have their own natural language processing libraries. 12 00:01:09,540 --> 00:01:16,230 However, Python is very popular for doing natural language processing, so it's very likely that Google 13 00:01:16,230 --> 00:01:18,150 Maps are using Python as well. 14 00:01:19,140 --> 00:01:20,760 Social media monitoring. 15 00:01:22,040 --> 00:01:30,050 That's a lot of posts and comments are being posted all the time, and some of those comments and posts 16 00:01:30,080 --> 00:01:32,690 can contain harmful language. 17 00:01:33,990 --> 00:01:41,610 So social media platforms such as Twitter or Facebook, they do have their algorithms which detects 18 00:01:41,610 --> 00:01:46,770 such language and they monitor it or filter it out, as Google Maps do. 19 00:01:47,980 --> 00:01:55,450 So to do that, natural language processing is used so that it is able to detect the meaning of words 20 00:01:55,450 --> 00:02:00,790 basically, and cross-check them with their natural language processing database. 21 00:02:02,400 --> 00:02:04,530 We have grammar checkers, for example. 22 00:02:04,560 --> 00:02:11,730 If you have something like grammarly or ginger, so these grammar checkers and if you have them on your 23 00:02:11,730 --> 00:02:15,480 browser installed as an extension and you are writing an email. 24 00:02:17,590 --> 00:02:24,070 Then the accession can tell you how optimistic or how hateful your texts can be. 25 00:02:25,580 --> 00:02:26,720 So for that. 26 00:02:27,490 --> 00:02:31,270 These grammar checkers are also using NLP. 27 00:02:33,480 --> 00:02:34,950 Email spam filters. 28 00:02:36,300 --> 00:02:39,560 Email servers such as Gmail and Outlook. 29 00:02:39,570 --> 00:02:47,070 They do have their algorithms which check emails that are coming to your inbox, and these algorithms 30 00:02:47,070 --> 00:02:51,390 decides whether these emails are spam or genuine emails. 31 00:02:53,380 --> 00:02:57,580 There are different factors to decide whether an email is spam or not. 32 00:02:58,580 --> 00:03:02,780 And one of these factors is related to sentiment analysis. 33 00:03:03,560 --> 00:03:10,910 So it checks all the language of those emails and it adds to the entire coefficient to decide whether 34 00:03:10,910 --> 00:03:12,680 the email is spam or not. 35 00:03:13,640 --> 00:03:21,530 So these were example more in the sentiment analysis fields to detect the mood, the tone of the language 36 00:03:21,740 --> 00:03:22,660 use. 37 00:03:22,670 --> 00:03:28,070 And then we have other parts of natural language processing. 38 00:03:28,670 --> 00:03:37,040 For example, Google Search uses an LP to try to understand your intent, what you are searching. 39 00:03:39,050 --> 00:03:46,070 For example, you might be searching on Google for how to code a chat bot with Python, and Google will 40 00:03:46,070 --> 00:03:53,510 show you websites which include this query how to call the chat bot in Python, but it will also show 41 00:03:53,510 --> 00:03:58,280 you websites which mention how to build a chat bot in python. 42 00:03:58,280 --> 00:04:03,440 So build and code are two synonyms here having the same meaning. 43 00:04:03,440 --> 00:04:13,040 So two words having the same meaning and google cross-check your search terms against NLP databases. 44 00:04:13,040 --> 00:04:20,209 So NLP also includes things like synonyms and that is part of natural language processing. 45 00:04:20,750 --> 00:04:23,870 Translators also use NLP. 46 00:04:25,130 --> 00:04:34,760 They also tried to understand the meaning of your text and not just translating your texts literally 47 00:04:34,760 --> 00:04:36,290 to the other language. 48 00:04:36,290 --> 00:04:37,970 For example, English to. 49 00:04:38,890 --> 00:04:40,750 Chinese or Japanese. 50 00:04:42,350 --> 00:04:45,960 So synonyms, for example, might also play a role here. 51 00:04:45,980 --> 00:04:54,860 Chat bots Chat bots work on intense classification, so you enter a text and the chat bot algorithms 52 00:04:54,860 --> 00:05:00,490 tries to guess the intense you have and it will give you an answer based on that. 53 00:05:00,500 --> 00:05:09,770 And for that chat bots will also use NLP in the course we will build chat bots, so stay tuned about 54 00:05:09,770 --> 00:05:10,280 that. 55 00:05:10,580 --> 00:05:17,690 And so these were a few examples of where NLP is applied in real world. 56 00:05:20,070 --> 00:05:21,210 Thank you for following this. 57 00:05:21,210 --> 00:05:24,810 And let's go further with more apps in the course. 58 00:05:24,840 --> 00:05:25,350 See you later.