Word2Vec Simplified|Word2Vec explained in simple language|CBOW and Skipgrm methods in word2vec

Word2Vec Simplified|Word2Vec explained in simple language|CBOW and Skipgrm methods in word2vec
#Word2Vec #UnfoldDataScience
Hello All,
Welcome to Unfold data science KZbin channel. My name is Aman and I am a data scientist.
About this video:
In this video, I explain the word2vec concept in detail. In this video, I talk about how Word2Vec works using skipgram and CBOW methods. I also explain how internally word embedding works and what are the benefits of word embedding. I explain in detail how embedding takes place and why it is so important in Natural language processing.Below questions are answered in this video:
1. How Word2vec works using skip gram and CBOW
2. What is Word2Vec
3. What is word embedding
4. Methods of word embedding
5. Continuous bag of words in Word2Vec
6. Skipgram in Word2Vec
About Unfold Data science: This channel is to help people understand basics of data science through simple examples in easy way. Anybody without having prior knowledge of computer programming or statistics or machine learning and artificial intelligence can get an understanding of data science at high level through this channel. The videos uploaded will not be very technical in nature and hence it can be easily grasped by viewers from different background as well.
Join Facebook group :
www.facebook.c...
Follow on medium : / amanrai77
Follow on quora: www.quora.com/...
Follow on twitter : @unfoldds
Get connected on LinkedIn : / aman-kumar-b4881440
Follow on Instagram : unfolddatascience
Watch Introduction to Data Science full playlist here : • Data Science In 15 Min...
Watch python for data science playlist here:
• Python Basics For Data...
Watch statistics and mathematics playlist here :
• Measures of Central Te...
Watch End to End Implementation of a simple machine learning model in Python here:
• How Does Machine Learn...
Learn Ensemble Model, Bagging and Boosting here:
• Introduction to Ensemb...
Access all my codes here:
drive.google.c...
Have question for me? Ask me here : docs.google.co...
My Music: www.bensound.c...

[@abdullahilawal3220]

Masha ALLAH, i have searched for three years to get a simple explanation of w2v until i found your video today. U have done a great job. Thanks alot

[@UnfoldDataScience]

Your comment made my day Abdullahi. thanks for such motivation. keep watching.

[@debbs_io]

Finally a simple, clear and complete explanation of this word embeddings. Thank you so much. I've studied and searched for months and you've just made the whole thing clear and straight forward.

[@victorsolomonmachinelearning]

I've been searching for a comprehensive explanation without the technical jargons. you are the best teacher

[@UnfoldDataScience]

Thanks Solomon.

[@dub161]

crazzzzyyy. You make things so simple!!!!

[@metalhamster14]

You have a gift. A natural teacher.

[@shivnathsinghgaur5972]

i spend too much time to get logic behind woed2vec but now i am satisfy

[@UnfoldDataScience]

Thanks for watching.

[@SaHaRaSquad]

Finally an understandable explanation of how those methods work. Short and to the point, thanks for this video.

[@MrBansal907]

Good job sir, thank you

[@caoilim]

I really don't comment but this is just great. Really helped me out with my college assignment. I was tearing my hair out before this. Genuinely thank you.

[@UnfoldDataScience]

Glad it helped!

[@LocksRevenge]

Simplified and concise, Thank you Sir.

[@arcanepersona1676]

May Allah increase your knowledge my friend, i am just starting with NLP and you help me learn the basics well. I didnt know what one hot embedding means. Thanks and keep it up. Also could you please do a project end to end in NLP for example sentiment analysis ? I want to see these techniques in real action. Thanks again :)

[@henriquemaulerborges1390]

You video is very simple to undestand, thank you man!

[@UnfoldDataScience]

Welcome

[@uwaisahamedimad556]

I have written the same in one of your previously watched video,but still I want to write it...You are really unfolding Data Science.

[@UnfoldDataScience]

Thanks Uwais. Your words mean a lot.

[@nikitasharma4957]

Jaise hi word or vector m difference smjh aaya i 👍 ❤️ like it seriously..after that I HV seen full vedio..osam explanation

[@gurmindersinghmalhotra8184]

Aman bhai, thanks for excellent explanation.

[@UnfoldDataScience]

Always welcome Gurminder Bhai.

[@SACHINKUMAR-zo5pm]

I find ur videos very helpful, many topics which are not explained well in other channels, i come to ur channel to see if it is available and u have never disappointed me. Keep up the good work. Thanks.

[@UnfoldDataScience]

Thanks Sachin. Please share with friends also

[@jialaiz9101]

Very intuitive, thx man

[@UnfoldDataScience]

welcome Jialai.

[@pankajuprety9216]

your explanation is simple clear and best

[@UnfoldDataScience]

Thanks Pankaj.

[@SallyMwalrMusic]

Just sending love and regards seem like a good person and appreciating your efforts to teach others,

[@ribamarsantarosa4465]

humble and nice presentation :)

[@UnfoldDataScience]

Thanks a lot.

[@mrdh927]

Thank you, Aman, I really appreciate your simple explanation.

[@UnfoldDataScience]

Most Welcome. Your comments are precious for me.

[@dhlpaket2247]

Best man

[@UnfoldDataScience]

Thanks again.

[@bekiofficialchannel9746]

Thank you! I got the basic concepts about word2vec.

[@sandipansarkar9211]

finished watching

[@vijaym4598]

Very simplified about Wrod2vec....Thanks and all the best

[@UnfoldDataScience]

Glad you liked it

[@mahikhan5716]

great aman . tactics of ur teaching is really tremendous

[@RezoanurRahman]

Literally can not make it more simpler than this.

[@UnfoldDataScience]

Thanks a lot Rahman.

[@RohanPaul-AI]

As always, superbly simple and great explanation. Many thanks.

[@UnfoldDataScience]

Welcome Rohan.

[@ShahzadKhan-zq9ty]

one of the finest explanation, thanks bro

[@UnfoldDataScience]

Thank u.

[@krishnabhadke6161]

Perfectly Explained , hats off to u!! Thank You

[@UnfoldDataScience]

You're most welcome

[@exuberantyouth8765]

Thanks Aman

[@piyalikarmakar5979]

Thank you so much sir.. From the documentations I was confused.. Thanks a lot for such cleared and easy explanation..

[@UnfoldDataScience]

Welcome Piyali.

[@linxin3811]

Very good introduction to Word2Vec. Would have preferred a bigger writing space, but nonetheless was very clear

[@UnfoldDataScience]

Glad it was helpful Kevin.

[@udayradhe6537]

Amazing! so well explained in simple terms.

[@UnfoldDataScience]

Thanks Uday

[@NightSurge.]

Great video, straight to the point and easy to understand.

[@UnfoldDataScience]

Cheers.

[@rejithmadhavan5735]

Precise explanation. Very useful. Thank you Aman. Just one suggestion, visually it will be more soothing if you could follow straight line on your whiteboard.

[@UnfoldDataScience]

Thanks a lot for suggestion.

[@karthickd537]

Very nicely explained in a very simple way.

[@UnfoldDataScience]

Thanks Karthick.

[@AbhishekKumar-hh5oh]

well explained and in a simplified way. Thanks a lot for this video

[@UnfoldDataScience]

Glad it was helpful Abhishek.

[@fatemeazizi2224]

simply explained, Thank you

[@pranjalgupta9427]

Nice explanation

[@UnfoldDataScience]

Keep watching Pranjal.

[@omkarjadhav13]

Good work.

[@UnfoldDataScience]

Thank you Omkar.

[@findyourpassion1677]

Very helpful explanation. Looking forward to seeing more. Thanks in advance.

[@UnfoldDataScience]

Glad it was helpful!

[@sunilupadhyay7948]

very informatics pls continue.

[@UnfoldDataScience]

Thank you Sunil, I will

[@vittalhundarad1644]

thank you sir , nice explanation

[@SibanandaPattanaik]

@Unfold Data Science In the starting whatever encoding ur doing, I don't think it is one hot encoding instead it's a BOW representation...Correct me if i m wrong.

[@UnfoldDataScience]

wil check

[@sharatchandra2045]

good and simple explaanation

[@UnfoldDataScience]

Thanks for liking Sharat.

[@aniketwagh570]

awesome video sir, really awesome.

[@UnfoldDataScience]

So nice of you Aniket. Your comments are precious for me.

[@learn-and-live]

thank you for this clear explanation!

[@UnfoldDataScience]

Thank you

[@unexpected2004]

Great stuff! Couldn't find a better video with such well assembled content.

[@UnfoldDataScience]

Glad it was helpful!

[@vaishnavibhosale2272]

great work 👍👍

[@pakistantechknowledge3911]

you mean sparse vector of word will give dense vector. how features are selected and how values are assigned ?

[@saqibcs]

Brother, great explanation. I will appreciate if could just tell where I can found next video

[@UnfoldDataScience]

Please check in my playlist for NLP

[@anurodhchoudhary1689]

when Legends start to teach everything becomes ezzzz!!!!!

[@UnfoldDataScience]

Thanks Anurodh.

[@RaghavaIndra]

Very good explanation!

[@UnfoldDataScience]

Thanks Raghava.

[@user-yy9vt2np7k]

thank you!

[@UnfoldDataScience]

You're welcome!

[@LearningWithFun333]

Great explanation. thanks a lot.

[@UnfoldDataScience]

You are welcome! Tabassum.

[@binaykumar1616]

You explained nicely. Please use a bigger screen.

[@UnfoldDataScience]

Thanks for watching and Feedback Binay.

[@the_street_coder4433]

Owosome Men, I Loved the explanation.

[@UnfoldDataScience]

Glad you liked it

[@sudiptamang1018]

thank you

[@UnfoldDataScience]

You're welcome Sudip.

[@sandipansarkar9211]

great explanation

[@UnfoldDataScience]

Thanks Sandipan.

[@juniormedjeufopa3780]

Thanks :) Great explanations

[@UnfoldDataScience]

Welcome.

[@suriebc6779]

Hi, I have an experience of 8 years in IT(Programming) and started preparing for data science career transition. My query is How can I put up in Resume. Shall I tell them that, I am new to this and Know all the concept and worked on kaggle datasets? Will they allow or reject since no past experience on data science? looking forward for your valuable comments.

[@UnfoldDataScience]

Hi, The query needs some bit of understanding your profile and giving suggestion I see you are looking for some career guidance, If yes, you can reach me directly for one on one mentorship. You can go to "About" section in the channel and click the link "One to One Mentorship Link"

[@shaheenullah3212]

Great sir. please sir also share about pos tagging using this approach

[@UnfoldDataScience]

Sure, will do Shaheen.

[@claudeclaude9991]

Man, you are great. Thanks a lot. Do you have any doc2vec video or playlist?

[@UnfoldDataScience]

Thanks a lot, doc2vec, I will create. Have not created yet.

[@omarwaleedsalihalrassam905]

Great explanation and well done, my question is how the numbers can be selected to set the features? I mean, in your example at time (5:00) of your video, you assigned 0.9 to the apple and 0.85 to mango ..etc, how these numbers can be assigned?

[@UnfoldDataScience]

We do not assign manually, framework assigns.

[@aqsashahzad5139]

Informative video... (y) Or in m sy best algorithm konsa h text classification tasks k liy cbow ya skip gram?

[@UnfoldDataScience]

Depends on what kind of data you are working for.

[@preranatiwary7690]

Good one again!

[@UnfoldDataScience]

Thanks again! Happy Learning!

[@syedharis3235]

Great job bro!

[@UnfoldDataScience]

Thanks for the visit Syed.

[@smartrider.strider]

Great stuff!

[@UnfoldDataScience]

Thanks Aditya.

[@omarsalam7586]

[@nagithareddy1798]

How to write a program to implement continuous bag of words model using knn algorithm (using python).

[@UnfoldDataScience]

Hi Nagitha, You can convert word to number and run KNN.

[@nagithareddy1798]

@@UnfoldDataScience could u please tell in detail I'm new to this course I donno how to do if possible please provide the code with explanation

[@mahikhan5716]

i have one question since bag of words has issue so isn't it used anywhere ?

[@UnfoldDataScience]

Mostly not used as it's very simple technique

[@prashanthkolaneru3178]

great stuff, where this application mostly used?

[@UnfoldDataScience]

Thanks Prashanth, in many NLP application where we need to capture semantic meaning of sentence.

[@paragpujari3961]

please do not put ads in between it creates distraction otherwise lecture is good

[@piyalikarmakar5979]

Sir, I have one query that as input we need to feed the one hot representation of the surrounding words including the one hot vector of the target word or excluding so?

[@UnfoldDataScience]

Hi Piyali. Excluding. For target you might need to do separate encoding.

[@piyalikarmakar5979]

@@UnfoldDataScience okay sir..then in case of getting all the word embeddings of the input sentence..one hot encode of the words under the window passed through CBOW and find the middle target word using the feature based information.. then slide the window and repeat the same untill the end... is it the process sir?

[@anagham2413]

How to increase the Dimensionality of feature vector

[@vijethrai2747]

By increasing output size more than 300 units you can get vector with higher dimensions and increase the model quality

[@UnfoldDataScience]

THanks Vijeth.

[@gururajraykar9254]

How Word2Vec will handle for Test data set?

[@UnfoldDataScience]

We need to create word vector for test and train in similar way.

[@maYYidtS]

bro how can we decide vector space size ex. (5000 words*300 vectors)...here 5000 is our vocab size, but how can we decide the 300 lengths...

[@UnfoldDataScience]

Normally we take 300 dimension however if our vocab size is huge, then processing might be difficult with more number of dimension hence we try limiting it to 200 or so. If you do not have infra issue, you can go for 500 or even more.

[@maYYidtS]

@@UnfoldDataScience Thanks....bro

[@maYYidtS]

@@UnfoldDataScience so it is considered as a hyperparameter?...can we change this in tunning. and please make video on optuna, biasen hyperparameter tunnign.

[@sidhantgi899]

Sir aap ne graduation kiss subject se kiya hai.

[@UnfoldDataScience]

Hi Rawat, I am BTECH.

[@sidhantgi899]

@@UnfoldDataScience B.tech Mechnical ya koi aur

[@sidhantgi899]

@@UnfoldDataScience ??

[@vihangafernando6644]

Are you using CBOW or Skipgram

[@UnfoldDataScience]

I Think CBOW, not sure though, the default one.

[@trexmidnite]

is nothing BUTT!

[@UnfoldDataScience]

Cheers 🍻