Day 7 | Salesforce AI Associate | Natural Language Processing | NLP | AI Bootcamp | Sanjay & Nikita

okay now going live okay so hello everyone I'm Sanjay Gupta I welcome you on Sanjay Gupta tech school so uh today we have one more session on AI so basically um as you all know U like uh we are having this uh Salesforce AI associate boot camp where different different topics are being covered and to cover one more topic that is natural language processing that is NLP uh I have Nikita with me so welcome Nikita on the channel and uh thank you yeah she will be sharing uh insights like what NLP is and uh what kind of questions you will you will be facing in the uh certification right so all the uh theoretical and conceptual things she will be discussing okay so I think we can start with the session over to you so um today we are going to have this uh understanding about natural language processing there are three words into it one is natural and the other one is language and the third word is processing natural means something which exist pretty usually and here we are talking about the human language which exists since years and ages and it's very uh common language it's something which only humans would understand obviously so we need to put in some efforts in order to make our computer learn so and then process and then come back with an outcome so this is what we are going to learn today that how exactly a computer would be capacitated enough would be enabled enough in order to understand the usual BAS basic human language that is what the gist of natural language processing is in a bit so let's see what definition of natural Pro uh natural language processing do we have so NLP is an area of research in the computer science and AI concerned with processing natural language such as English or any other language it is vastly used everywhere in the world so we do not have to only comply with English we can comply with any language that we want your language whatever you speak would be would be translated would be entered into the NLP model and then it will process it and then it is going to give you the output after lot of parsing and techniques that it is going to understand your language by right so this processing generally involves translating natural language into Data you should be very much um uh understanding that whatever we write whatever we say verbally is understood in a format and that format is not the linguistic format obviously if we are entering something there not be a possibility that the model understands it in that way it has to segment it it has to take those characters words phrases paragraphs and then comprehensions into a totally different way and that's how it is going to process it up so this is what the whole terion of NLP looks like now it started in 1950 with the alen during test and I have discussed this aluring test in my day Zero Channel sorry day Zero video where you can go and check what exactly aluring did in 1950 and after that the first use case of natural language processing came into play which was language translation from French to Spanish from English to Spanish from you know Russian to uh any other language so these are the first use cases of natural language processing where I can type anything and it is going to give me a translated version of whichever language I want to enter into it right so let's just have this uh clue about this last paragraph that I was studying this processing generally involves translating natural language into Data numbers that a computer can use to learn about the world and this understanding of the world sometimes is used to generate natural language text that reflects that understanding so if I take the example of Chad GPD I am entering my text so this text can be anything right and if I'm going to enter into it like give me the details about natural language processing give me the details about Wildlife so it is going to understand it process it now processing it's not just a word there are various techniques involved in this processing which we will learn extensively in near future and uh after that it is going to give you the result character by character or word by word or line by line so when you type something in chat GPD you must have seen that the output is written in such a way that you know character by character or words by word come in and you just watch it like it is it looks like it is typing those words correct it's not like a paragraph is just thrown on your face it's not like that it keeps on typing typing typing and that's how the character conversion is coming into play so this is what the first slide of mine would explain to you then of course we have sub areas of NLP now what actually holds this holds inside this NLP is natural Lang understanding and natural language uh generation these are two parameters or you can say the two impactful uh configurations inside this NLP which enable this NLP to actually result into U human language where it is going to understand your stuff and it is going to generate an output with respect to whatever it has understood in a way well whatever we speak comes up with a vocabulary and these are some of the uh list I should say this is a list which I have uh you know enlisted over here where you can see that natural language encompasses what all how is a natural language made any language is made up of a definite vocabulary if you do not have the words to say your feelings say your uh sentiments then you are unable to communicate right so for any communication you need your words you need a different set of vocabulary now be it any language it's not of course about English it can be about any language that you are uh you know comfortable in so vocabulary is one of the things then grammatical errors that you know there might be some grammatical errors when you put in or plug in or input your language so this grammar has to be taken into consideration that how you are speaking what you're speaking and is it coming out with any sense has it got any sense and you know whenever we say that he asks me or he asked me it has a viable difference so you should know that grammar is going to play a lot of role in whatever you want to insist to the model and get the output for then you have the syntax now you should understand that if I am writing in in a Soro syntax the computer would also result into its syntax so initially it was a problem that you know my words uh would be in certain Manner and then the output would just generate the you know the output in a manner where the synchronization was not done so these were the drawbacks which were certainly worked on since 50 years NLP is into uh you know into the working and we have been researching so much more now the results are pretty optimized and we can get the output in a language and something which is very making sense so this is what a syntax importance is then you have semantic means the meaning of the words the phrases and sentences pragmatics of the sentence again the context and the intent behind that means reading in between the line comes up with a huge importance your model should be able to understand what are you trying to say rather than just emphasizing on what text you have input so this is pragmatics where your sentiments and your intent of saying anything delivering anything is taken into consideration then you go to discourse and dialogue of course how do you say that matters again so units larger than a single phrase or sentence including documents and conversation all of them are taken into consideration then you have phonetics and pH uh phology so this means that the sound we make when we communicate for example we have Alexa and Siri so when I talk to Siri I need to be very clear about the fact that you know play this song If I'm not clearly delivering my idea of playing a song Siri would say like Siri either would generate an outcome which is based on what it has heard or at least it would not be correct if my communication has gotten disrupted with any of the ill ill phonetics if I've used any correct so this is how your Siri and Alexa work they need to have concise precise uh verbal uh communication and if not so they would either deny the results or would generate the results which are not so uh useful for you last we have morphology that means how parts of the words can be combined or uncombined in the and combined to make the new words that's about how the natural language has got its own instincts and how it should be delivered in order to get the desired outputs then we hop on to the area where we are now going to realize that how exactly is uh NLP working how in the field is it actually delivering the results which is which it is delivery so NLP uses algorithms and methods like llm statistical models machine learning deep learning and Rule based systems to process the process and analyze your text these techniques are called parsing this parsing is very very important for you guys in order to uh clear the AI associate exam there'll be various questions on this parsing they'll be asking you what is segmentation what is semantics what is lemmatization all these techniques will be asked and you should be knowing everything in a briefed or concise manner otherwise uh you you'll lose marks of course and might not get the certificate so these techniques are called parsing involving breaking down the text into chunks now the model is not efficient enough to directly understand the paragraph whatever it is of course if I am reading anything I am also either understand it by the context or I'm understanding it by the you know vocabulary so I have got a sense of understanding so the way I am understanding this might not be the way our computer wants to understand so there are various tokenized way in which the computer or model would understand now the way you break the paragraph the way you uh you know segment your paragraph or line that this segmentation lemmatization all these processes are imposed on the text that you put in right so these techniques you have to be very careful about um learning so that you know you are able to gain your desired achievements sorry I think my screen went off yeah I think you can again slideshow yeah what so maybe you can jump on to the next slide and then slideshow my writing pad was actually connected it was making some okay sorry no problem so here we have parsing which is divided into two segments one is syntactic parsing and the other one is semantic parsing syntactic parsing looks at the general grammatical syntax rules um your words how are they phrased all stuff semantic is little sentiment analysis your in between the lines inferences that's what semantic parsing would look like so these are two types of parsing that you would majorly see in the sales for sales force trial head program so here you go with the first thing which is parsing what does a syntactic parsing look like so you can see that syntactic parsing is where elements of natural language are analyzed to identify the underlying grammatical structure so when you're talking about syntactic paring you're talking about General grammatical structure how it has to be broken down into different segments and then it should be inferred in a way by the model and and then interpreted and then the output so you can see that the sentence is on the top it has been broken down into the noun phrase verb phrase the noun phrase is then uh characterized as it is either proper noun or what kind of noun is there so that type of phrase it would be so proper noun phrase and you know that the proper nouns are all the names that we have so if it would have been a city name or anything like that it would have been characterized in the proper noun name then verb phrase you have got it is characterized into the verb and other noun phrase that if it has any so that verb is eight then finally we have a noun phrase which is further characterized into determiners and noun noun is another one which is Apple and determiner is a an so this is how the characterization of a statement or line looks like when you talk about paring so these are the two types of parsing that you see in trial head program yeah here just want to add one thing why as you mentioned like we need to uh know the specific things about these uh uh techniques right so why so why these are important because uh whenever anyone is appearing in the exam so there will be like uh three options available and it is too confusing like which one to select it seems like every option is correct so if you if you know the specific uh meaning or uh explanation of a particular topic so it will uh prepare you to identify the correct option uh immediately as you read the question right so that's why if you go through all the session in detail and try to understand the concept then uh I don't think you need to U you need to you you don't need to use any any sort of dumps which are popular so just try to understand the concept so that you clear the certification and whenever you are going for an interview there also you can explain those topics in detail okay yeah um please go ahead correct okay so now we are going to uh characterize or classify the syntactic parsing as well into its various uh different different sort of uh techniques that it has been classified into the first one is segmentation then we have tokenization mostly the question is asked between stemming and lemmatization then you have parts of speech tagging and named entry recognition the last two are simple pretty simple where you know you can just have a read and you get get done with it it's there in the trial head program however here we have this holistic application of segmentation tokenization stemming and lization so we'll look at segmentation today where we have larger texts are divided into smaller and meaning meaningful junks uh segmentation is a process where you uh you know put into pieces some sort of text that you have so it could be either large text or it could be even a word even a even a sentence anything that has to be segmented into its stems and prefixes suffixes so these things are grammatical things if you have ever heard about prefix prefix is what is attached at the beginning suffix is what follows so these are two words that you should be clear about that segmentation does so segmentation usually occurs at the end of sentences at punctuation marks to help organize the text for further analysis so this is what segmentation does it makes the larger chunks smaller and larger sentences smaller by putting them into pieces of and characterizing them with their respective uh things like if it is at the beginning it's called prefix if it is in the end it's called the suffix the next is called tokenization tokenization is again it is a subset of segmentation only but as you can see that this I have made this uh image ready where you have you've been given this this is a sample and if I would tokenize it it would result into different words this is a sample so this is how the chunks are broken into a a format and then stored into the model so it is a pre-processing step in which a long string of text is broken down into smaller units called token tokens include words characters and subwords always it is not going to characterize a word into suffix or prefix but it is going to break it into the chunk I mean the chunk is broken down into the small words so they are the building blocks of natural language processing and most NLP models process raw text on the on the token level so now what after this after you have broken this um worded format after you have gotten this worded format after this you will learn a vector analysis where these U words will be stored in the form of matrices and all you know stuff that we are going to do in the mathematics part of the NLP later on so here up till now it's just about theoretical aspect of tokenization where you can study that the sentence is broken down into small words this is about tokenization yeah I I remember like when I um started learning Java and taught as well so in Java also this tokenization concept is available able and in in most of the programming languages like uh we store this data in in form of string and we have some predefined methods through that we can divide U different words into different tokens so yeah it is good like it is used here also so those those who are from programming background watching this session they can relate like how tokenization is already done in the programming and that is included here for pre-processing right yes just the way compiler was there in any programming language we have an interpreter or a compiler right yeah so they change the low level language where we input into the Assembly Language or high high level language right I think that's what the thing is so this is how um the compiler or interpreter you know they they get and do the desired things and then they store into and then they perform some actions so that's how the I think I think sorry the high level language is converted into the low level language yeah and then finally the you explained it in reverse yeah yeah yeah yeah so yeah I mean this is what happens there when we interact through any programming language when we interact to any of the you know like if it is python ID or if it is C programming ID whichever it is so if you have to interact with that you have to have a compiler or interpreter now here we don't have that case it's just a human language and human language has to be made understood by to the computer so how do we do that this is the process of uh you know doing such things yeah then you have stemming stemming and lemmatization again very very important we have a quiz question based on this so you focus over here the words are reduced in the root form they're also called the stem so you can see that stud studies and studying both have got different Roots one is study one is study right so this is what stemming does it doesn't grabs any sort of grammatical technicality however it only uh takes a part of the word out which it thinks that it is common and then you know gives you the desired part of the word so it doesn't have to be very grammatically apt this is what the difference between LZ and steming is lonization is a pretty forward technique it is little costlier also and uh it is updated version of steming as also we can say so for example breaking breaks or unbreakable are all reduced to the word break so stemming helps to reduce the variations of words forms but depending on the context it may not lead to the most accurate stem so look at the two example that use stemming so so here you can see that stemming is how we have used and it is going to remove the suffixes out here right and study and study both are taken as the roots of the word now what how is it different from lemmatization let's see that lemmatization is a more sophisticated technique that uses morphological analysis to find the base form of the word it is also called Lemma Lemma is the base form of the word lemmatization produces the words to their root and also takes into account the part of speech so part of speech means whether it is a noun whether it is a you know verb all the parts of speech like interjection preposition these are all parts of speech so these are taken into account to arrive at much more valid route or Lemma so both as you can see studies and studying have gotten a single root study which is a more apt root rather than the two roots that we got for stemming stod Y and sodi so what is a difference between stemming and lemmatization you can see that stemming is resulting into one root which is Chang which is not of any meaning over here from the words like change changing changes changed changer then you have lemmatization where it is change changing changes all these words are taken into consideration and a single word which also makes sense has been taken out is called change so lemmatization is a pretty forward technique and it is useful as well in after the stemming preprocessing technique if if we can summarize so in stemming we just removed the suffixes right and in lization instead of removing like along with removing suffixes we uh like there there's a word created which make more sense of those combinations yeah yeah I think with this with this diagram it is very easy to remember the differences between stemming and lization correct correct so if I would take you now to the parsing techniques which are related over there in the Salesforce child head and you have a quiz over there I think now you will be able to uh take it also so let me share the screen check yeah so guys uh here you can see uh uh this trail head module uh if you can scroll up I one second here it is the uh can you go back uh one more time yeah one more time yeah here it is so guys this we have covered yeah go ahead we have covered gener generative AI basics in the previous lectures now we are on to this natural language processing Basics after that we'll go on to the data fundamentals for AI so this is the last lecture for the NLP that you're going to hit today yeah so here we have two modules right so uh have you covered both the modules or like only no no we are we are covering the second module the previous one had just got this aluring test which I have already discussed in the da lecture okay okay so yeah if you can come over here and see which NLP technique uses the paths of speech to more accurately find out the root of the word so this is how the questions can come yeah I can okay you decide I think it is D lemmatization let's see and then you have what is a term for finding the underlying structure of text in NLP it's it cannot be parts of speech because that's a theoretical uh thing it's not a technical thing hence we can escape it sentiment also it's the thing that you know how human have got the emotions into them and how they are depicting their emotions so it's their sentiment so again these two things are cannot be so morphology is a technique of like morphology is where you know you combine and uncombine words okay to give to generate new words so again this is also not going to be there only under to what is the term for finding the underlying structure would be parsing okay that's what we have studied now and this is how we can go let's see yes yeah both are correct if if you can if you can cover the first one also can we have it again I'll go I'll go I'll go yeah I think it is there if you scroll down so okay so you have natural language processing over here then that I have already covered then you have discussed everyday uses of the NLP uses we are going to take right now and the used cases of energy we take then you have explained how it has evolved since 1950 so you can see that here there's a brief theory about tent uring and we have already covered this experiment in our day Zero I started with this experiment in the day Zero where artificial intelligence was introduced so they can watch the day Zero where it has been in a glance explained very well yeah I think those who are interested and joined in between they can just so U if if you're watching this uh boot camp session for the first time so uh like we we will request if you can go through from the day Zero so that you can relate all the topics right so U having having AI associate certification U is becoming U good to have or nice to have and U like if you don't like reading theoretical things you want to listen uh someone who is explaining the topics so I think uh uh this this channel is the first channel in the entire e Salesforce ecosystem where uh you will find AI related U uh sessions totally free of cost so just just utilize all those sessions step by step so that you Lear things quickly we also had discussed about what is natural language can you answer what is a natural language according to you what would it be uh I think number two the way human humans communicate right and then if we go on to the next one in what ways have neural networks impacted the en uh A and B uh so answer will be D I think it should be correct yep okay so I think uh we we are good with this uh topic now and anything else that you want to cover yes of course I I'll just end it on uh the Ed cases that's what we'll end it on I think a couple of slides and I'll just okay yeah we have we have two more slides pleas yep we have we have time so you can go ahead okay now you have the used cases of NLP so the first one is email filters so email filters means whenever there's a Spam sort of an email where you know there are a lot of shopping sites that are constantly sending you these messages through the uh email that you know you you can buy this you can buy that and we have got good offer so your email filters what they will do is recognize the certain pattern in those text which are spams or certain words certain phrases certain texts that's how the email filters will work and filter out all the spams so that you are only having a very scrutinized number of mails in your mailbox rest other go into the spam box so that's why sometimes what happens is even some Sometimes some mails which are of importance so they ask you to check the Spam mailbox that it might be a possibility that 10% doubt can be there that you know this the email that they have sent is sent into the spam box so that's the email filter thing so then you have text pred you you are sharing trail head uh page so you want to share the slide because otherwise audience will think session is ended and they will think what what she is talking about here you have used cases of MH so the first one is the email filters in email filters what do we have I was explaining you the email filters right so in email filters we have a thing called spam analysis now this is not a written thing over there but what through email filters we have is we we find out that you know what kind of text what kind of words are rela to the spams and when we as I mentioned that you know whenever any shopping website is constantly sending you mails then it is automatically uh sent to the different sent to the different uh mailbox which is Spam box right so that's how they categorize the spam either on the words text phrases these sort of of things are analyzed with the email filters so I have a explanation for it the first used case of NLP is email filtering it began with the spam filters uncovering certain words or phrases that signal a Spam message so how do you signal the spam message by uncovering certain words then you have GMA Gmail email classification so it recognizes if males belong to one of the three categories one is primary social or promotions based on their contents for all Gmail users this keeps your inbox to a manageable size with important relevant emails you wish to review and respond to quickly this is what email filters would do then you have the next thing which is very very important so I have made these uh uh snapshot also because I tried to uh you know exemplify the NLP uh text prediction thing so if you can see I have written a mail to random gmail.com where I have typed some certain text over here so this mail is to remind you of the negotiation that we have had in our in R and then while I was writing the L they already predicted the last meeting so if you I if I would zoom in you'll see that it is in the gray format which is is something that I have not written but they the email or the Gmail has predicted the output so this is what text prediction looks like then you have the next thing which is looking forward to your now if I have written looking forward to your then I have written this uh positive I not written the positive thing and they have understood it by themselves this would be a probable output here so this is how text prediction works and the final thing yours and after writing yours they already said or they predicted that sincerely would come so this is how the email in email the text prediction works like last we have the smart assistance as a use cases of NLP Apple Siri and Amazon's Alexa I have discussed it numerous number of times and this is again probably I'll say that whenever you make some sound that you know this is what you want and when you communicate with them verbally you have to be pretty clear and then they are going to analyze those patterns in whatever you're saying so when you play that play this song play that song they're going to do so however if you would ask them to play your favorite song they might be a little skeptical because they don't know what your favorite song is so either you make a list of your favorite song and input that or you will have no output for it because what's your favorite song they can recommend you on the basis of whatever you have heard many a number of times but it's not always going to be a spot answer that this is your favorite song right so they can recommend you what your favorite song can be on the basis of what all songs have you heard before but in order to have a spot answer you have to tell them that this is your favorite answer and this is what they have to play when you ask for a favorite answer or favorite song and how do we talk to Siri it's like if we want to to ask anything we just activate Siri by saying Hey Siri ask a question and then she understands what we said and responds in a relevant answer based on the context so this is how NLP works and that's it for the day okay so I think you uh covered a lot and U so in this session like NLP is all covered nothing is left right okay and what will be the next topic the next topic will be data you know what is the significance of data in the AI okay that income passes I get 38% of the associate program right so yeah we have we have four modules so first we already completed uh fundamental of a I think we are covering the second one right now and generative AI predictive Ai and NLP these three topics we already covered and U data data in data with AI I think it is it is the fourth module right okay yep so I think uh those who are following all the sessions they are understanding and uh if you if you keep following all the sessions I'm sure um by following only these sessions you will be able to to crack your AI associate certification so I just want to give a thank to Nikita for preparing all the content and sharing all the knowledge U freely with the community so thank thanks thanks for that and uh uh I know like uh you you are planning to do uh one more uh boot camp that will be more practical oriented right so here we are just discussing all the theoretical Concepts but in that boot camp uh she will be first explaining what python is and how we can use Python to build models in AI uh right so we are planning that as well so maybe this month we will be completing this boot camp first so that at least you can Target AI associate certification and then we will plan that boot camp so that uh on on broad level you can understand how actually uh something can be built in AI right okay so that's it for today thank you for joining this session and uh if you're watching the recording thanks to you as well so keep following all the sessions if you want to uh clear your AI associate certification okay thank you thank you everyone thank you Nik uh so we'll see you in the next session guys