Word2Vec - Skipgram and CBOW

Поділитися
Вставка
  • Опубліковано 25 лис 2024

КОМЕНТАРІ • 133

  • @rma1563
    @rma1563 8 місяців тому +4

    By far the best explanation of this topic. It's crazy you only took 7 minutes to explain what most people spend a lot more and still can't deliver. Thanks ❤

  • @nax2kim2
    @nax2kim2 3 роки тому +7

    indexing for me
    2:40 Word2Vec exam
    3:06 CBOW
    3:20 Skip Gram
    -----
    5:30 CBOW - working
    5:50 Skip Gram - working
    6:30 Getting word embeddings
    thx for this video :)

  • @iindifferent
    @iindifferent 4 роки тому +21

    Thank you. I was having a hard time understanding the concept from my uni and classes. After watching your video I went back and reread, and everything started to make more sense. Went back here watched this a second time and I think I have the hang of it now.

  • @user-fy5go3rh8p
    @user-fy5go3rh8p 4 роки тому +13

    This is the best explanation I've encountered so far. Thank you!

  • @fabricesimodefo8113
    @fabricesimodefo8113 4 роки тому +15

    Exactly what i was searching for ! so clear. Sometime you just need the neural network structure in details in graph or visually. Why don't many people do that ? Its the simplest way to understand what is happening in real in the code after

    • @TheSemicolon
      @TheSemicolon  4 роки тому +2

      This is what I needed when I was creating it, but did not find it anywhere :)

  • @subhamprasad6808
    @subhamprasad6808 3 роки тому

    Finally, I understood the concept of Word2Vec after watching this video. Thank you.

  • @Amf313
    @Amf313 2 роки тому +4

    Best explanation I saw through Internet to illustrate how Word2Vec works. Paper was a little bit hard to read; Andrew Ng's explanation was somewhat incomplete or at least ambigious to me, but your video made it clear. Thank you🙏

  • @jiexiong8522
    @jiexiong8522 7 місяців тому

    Other word2vec videos are still intimidating even after a lot of graph and simplification. Your video is so friendly and helped me understand this key algorithm. Thanks!

  • @sheshagirigh
    @sheshagirigh 5 років тому +10

    Thanks a ton. By far the best i could find after a lot of searching.. even better than few from stanford lectures!

  • @chihiroa1045
    @chihiroa1045 Рік тому

    Thank you so much! This is the most clear and organized tutorial I found on Word2Vec!

  • @maqboolurrahimkhan
    @maqboolurrahimkhan 3 роки тому

    Best and easy explanation of word2vec over the internet. Keep up the good work
    Thanks a ton

  • @thunder-v8h
    @thunder-v8h 4 роки тому +2

    Thank you sir! I always come back to this video when I forgot about the concept.

  • @skipintro9988
    @skipintro9988 3 роки тому

    Thanks, bro - this one is the easiest and simplest and quickest explanation on word2vec

  • @pushkarmandot4426
    @pushkarmandot4426 5 років тому +5

    The best video. Explained the whole concept in a very short amount of time

  • @anujlahoty8022
    @anujlahoty8022 Рік тому

    Simple and eloquent explanation.

  • @MuhammadQasim-f7d
    @MuhammadQasim-f7d 24 дні тому

    Best Explanation so far mate :) Keep up the good work!

  • @rainoorosmansaputratampubo2213
    @rainoorosmansaputratampubo2213 4 роки тому

    Thank you so much. with this explanation I can understand it easier than read from books

  • @tylerlozano152
    @tylerlozano152 5 років тому +6

    Thank you for the thorough, simple explanation.

  • @mohajeramir
    @mohajeramir 3 роки тому

    this is the best explanation I have found. thank you

    • @TheSemicolon
      @TheSemicolon  3 роки тому

      Glad you found it useful, do share the word 🙂

  • @ajinkyajoshi2308
    @ajinkyajoshi2308 2 роки тому

    Very well done!! Precise and to the point explanation!!

  • @jamesmina7258
    @jamesmina7258 4 місяці тому

    Thank you. I learned a lot from your video.

  • @FTLC
    @FTLC Рік тому

    Thank you so much is was so confused before watching this video ,now its clear to me

  • @jusjosef
    @jusjosef 4 роки тому

    Very simple, to the point explanation. Beautiful!

  • @romanm7530
    @romanm7530 2 роки тому

    Диктор просто огонь!

  • @bryancamilo5139
    @bryancamilo5139 8 місяців тому

    Thank you, your explanation is great. Now I have understood the concept 😁

  • @HY-nt8nk
    @HY-nt8nk 3 роки тому

    Good work! Nicely explained.

  • @nithin5238
    @nithin5238 5 років тому

    Very clear explanation man.. you deserve slow claps

  • @befesa1
    @befesa1 6 місяців тому

    Thank you! Really good explanation:)

  • @aravindaraman8667
    @aravindaraman8667 3 роки тому

    Amazing explanation! Thanks a lot

  • @Zinghere
    @Zinghere 2 роки тому

    Great explanation!

  • @varunjindal1520
    @varunjindal1520 3 роки тому

    This is indeed very good video. To the point and covers what I needed to know. Thank you.

    • @TheSemicolon
      @TheSemicolon  3 роки тому

      Glad you found it useful, do share the word 🙂

  • @johncompassion9054
    @johncompassion9054 7 місяців тому

    4:50 "5X3 input matrix is shared by the context words". what do you mean by input matrix? Do you mean the weight matrix between the hidden layer (embedding) and the output layer?
    5:18 "You take the weight matrix and it becomes the set of vectors". We have two weight matrices so which one? Also, I guess our vector embedding is the middle layer output values not weights. Correct me if I am wrong. Thank you.

  • @iliasp4275
    @iliasp4275 3 роки тому

    thank you , The Semicolon.

  • @MrStudent1978
    @MrStudent1978 4 роки тому

    Absolutely beautiful explanation!! Very precise and very much informative....Thanks for your kindness. Sharing one's learning is the best thing that a person can do to contribute to the society. Lots of respects from Punjab India....

  • @theunknown2090
    @theunknown2090 6 років тому +2

    Hey in cobw and skip gram
    Method there are 3
    Weight metrics
    Which metric is selected as d embedding matrix ? And why

  • @AdityaPatilR
    @AdityaPatilR 4 роки тому

    If hope can set us free hope can set you free as well !! thank you for the explanation and following what you preach ;)

  • @ogsconnect1312
    @ogsconnect1312 5 років тому

    I cannot say anything but excellent. Thank you

  • @carlrobinson2926
    @carlrobinson2926 5 років тому

    very nice explanation, not too long, straight to the point. thanks

  • @shikharkesarwani9051
    @shikharkesarwani9051 5 років тому +9

    The weight matrix should be 5x3 (input to hidden) and 3x5 (hidden to output) @The Semicolon

  • @impracticaldev
    @impracticaldev 2 роки тому

    You earned a subsciption. Good luck!

  • @coolbowties394
    @coolbowties394 4 роки тому

    Thanks so much for this thorough explanation!

  • @absoluteanagha
    @absoluteanagha 3 роки тому

    Love this! Such a great explanation!

  • @satyarajadasara9000
    @satyarajadasara9000 4 роки тому

    Very nice video where everything was to the point! Keep posting such wonderful content!

  • @OorakanaGleb
    @OorakanaGleb 5 років тому

    Awesome explanation. Thanks!

  • @gouripeddivenkataasrithbha5148
    @gouripeddivenkataasrithbha5148 4 роки тому

    Truly the best resource on word2vec by far. I have only one doubt. What do you mean by size of a vector being three. Other than this, I was able to understand everything.

    • @TheSemicolon
      @TheSemicolon  4 роки тому

      the size of final vector for each word is the size of word vector.

  • @anindyavedant801
    @anindyavedant801 5 років тому +6

    I had a doubt, shouldn't the first weight matrix with which the input is multiplied be of dimensions 5x3 as all the connections need to be mapped to the hidden layer matrix and we have 5 inputs and 3 nodes in the hidden layer so the weights would be 5x3 and the second one would be vice versa i.e. 3x5

  • @hardikajmani5088
    @hardikajmani5088 5 років тому

    Very well explained

  • @vid_sh_itsme4340
    @vid_sh_itsme4340 4 місяці тому

    is hierarchical softmax used in this?

  • @ankursri21
    @ankursri21 5 років тому

    Thank you.. very well explained in shorter time.

  • @keno2055
    @keno2055 2 роки тому

    Why does the hidden layer at 4:59 have 3 nodes if we only care about the 2 adjacent nodes?

  • @mohitagarwal437
    @mohitagarwal437 3 роки тому +1

    Best bhai aapne pura data science kar rakha hai kya ?

  • @mohajeramir
    @mohajeramir 4 роки тому

    this was excellent. Thank you

  • @md.prantohasan9630
    @md.prantohasan9630 5 років тому +1

    Excellent explanation in a very short time. Take

  • @bloodzitup
    @bloodzitup 5 років тому

    Thanks, my lecturer had this video in his references for learning word2vec

  • @hashinitheldeniya1347
    @hashinitheldeniya1347 4 роки тому

    can we cluster word phrases into groups using this word2vec technique?

  • @ashwinrameshbabu2418
    @ashwinrameshbabu2418 3 роки тому

    At time 5.28, cbow , hope gives 1x3 and set gives 1x3 dimension output. How are they combined into 1 (1x3) before sending to final layer?

  • @imanbio
    @imanbio 4 роки тому

    Plz fix the matrix sizes (3x5 should be 5x3 and vice versa..) - nice presentation

  • @MehdiMirzapour
    @MehdiMirzapour 5 років тому

    Thanks. It is really a brilliant explanation!

  • @fahdciwan8709
    @fahdciwan8709 4 роки тому

    what is the purpose of multiplying the 3*5 Weight Matrix with the one-hot vector of the word? How does it improve the embeddings?

    • @SameerKhan-ht4mx
      @SameerKhan-ht4mx 2 роки тому

      Basically the weight matrix is the word embedding

  • @057ahmadhilmand6
    @057ahmadhilmand6 Рік тому

    i still dont get it, the word vector for each word is a matriks?

  • @himanshusrihsk4302
    @himanshusrihsk4302 5 років тому

    Really very useful

  • @Hellow_._
    @Hellow_._ Рік тому

    how can we give all input vectors in one go to train the model?

  • @nazrulhassan6310
    @nazrulhassan6310 3 роки тому

    fabulous explanation but I need to do some more digging

  • @juanpablo87t
    @juanpablo87t 2 роки тому

    Great Video, thank you!
    It is very clear how to extract the word embeddings in skip gram by multipliying the W matrix with the one hot vector of the corresponding word, however I can't figure how to extract them from the CBOW model as there are multiple W matrixes, could you give me a hint or a maybe a resource where this is explained?

  • @parthpatel3900
    @parthpatel3900 5 років тому

    Wonderful video

  • @TheEducationWorldUS
    @TheEducationWorldUS 4 роки тому

    nice explanation

  • @Mr.AIFella
    @Mr.AIFella 9 місяців тому

    The matrices multiplication not correct. I think it should be 5x1 1x3 to be equal 5x3 to be multiplied by 3x1 to equal 5x1. Right?

  • @tobiascornille
    @tobiascornille 3 роки тому

    Which matrix is the embedding matrix in CBOW? W or W' ?

  • @naveenkinnal5413
    @naveenkinnal5413 4 роки тому

    Just one question. So the final word vector size is the same as sliding window size?

    • @TheSemicolon
      @TheSemicolon  4 роки тому

      No, sliding window can be of any size.

  • @hadrianarodriguez6666
    @hadrianarodriguez6666 4 роки тому

    Thanks for the explanation! If I want to work with terms of two tokens, how can I do it?

    • @TheSemicolon
      @TheSemicolon  4 роки тому

      you may want to append them may be ?

  • @muhammedhassen4354
    @muhammedhassen4354 5 років тому

    easy way explanation gr8

  • @aliqais4896
    @aliqais4896 4 роки тому

    thank you very much

  • @alialsaffar6090
    @alialsaffar6090 6 років тому +1

    This was enlightening. Thank you!

  • @DangNguyen-xx3zi
    @DangNguyen-xx3zi 4 роки тому

    Appreciate the work put into this video, thank you!

  • @gauharahmad2643
    @gauharahmad2643 5 років тому

    Sir what do we mean by size of each vector in 4:37 ?

  • @dhruvagarwal4477
    @dhruvagarwal4477 4 роки тому

    What is the meaning of vector size?

  • @josephselwan1652
    @josephselwan1652 3 роки тому

    it took me 10 times to understand it. but i finally did. lol
    what we do to get a job haha

  • @prathimads2876
    @prathimads2876 5 років тому

    Thank you so much Sir...

  • @qingyangluo7085
    @qingyangluo7085 4 роки тому

    how to get the word embedding vector using CBOW? what neighbour words do i plug in?

    • @TheSemicolon
      @TheSemicolon  4 роки тому

      You have to iterate over a corpus. Popular ones are Wikipedia, google news etc.

    • @qingyangluo7085
      @qingyangluo7085 4 роки тому

      @@TheSemicolon Say I want to get the embedding vector of the word "love", this vector depends on what context/neighor words I plug in.

  • @Simply-Charm
    @Simply-Charm 4 роки тому

    Thank you

  • @theacid1
    @theacid1 4 роки тому +1

    Thank you. My prof is unable to explain it.

  • @saikiran-mi3jc
    @saikiran-mi3jc 3 роки тому

    No much content in the channel to subscribe(i mean to say no playlist on nlp or cv ) .I came hear with lot of hopes. Content in the video is good.

  • @BrunoCPunto
    @BrunoCPunto 3 роки тому

    Awesome

  • @randomforrest9251
    @randomforrest9251 3 роки тому

    nice slides!

  • @pranabsarkar
    @pranabsarkar 4 роки тому

    Thanks a lot!

  • @sunjitrana374
    @sunjitrana374 5 років тому

    Nice explanation, Thanks for that!!! One question: How to decide optimal length of hidden layer? here in example its 3 and in general you said it's around 300.

  • @MultiAkshay009
    @MultiAkshay009 6 років тому

    great work! 😍I am really thankful to you. But still I have a doubt with implementation part. 1) How to train the models for new datasets? 2) How to use both approaches differently CBOW and Skip-gram for training of the models? I badly need help with this. :(

    • @TheSemicolon
      @TheSemicolon  6 років тому

      Thanks a lot.
      If you are implanting it from scratch then you have to encode each word of your database as a one hot vector train it using anyone of the algorithm skipgram or cbow and then pull out it's weights. Then multiply the weights with the one hot vector.
      The tensor flow official blog has a very nice example for it.
      You may use libraries like gensim to do it for you.

  • @hs_harsh
    @hs_harsh 5 років тому

    Sir can you provide the link of slides used. That would be helpful. I'm a student at IIT Delhi and I have to deliver a similar lecture presentation. Thank you!

  • @arnav3674
    @arnav3674 6 місяців тому

    Good !

  • @tumul1474
    @tumul1474 5 років тому +1

    awesome !!

  • @abdallahessam4671
    @abdallahessam4671 2 роки тому

    Correction, the English language has 600,000 words, only the Arabic language has this number that you mentioned is more than 12 million words

  • @ms10596
    @ms10596 5 років тому

    So helpful

  • @prajitvaghmaria3669
    @prajitvaghmaria3669 6 років тому

    Any idea how to create a deep learning chatbot with keras and tensorflow for WhatsApp platform using python from scratch ?

  • @_skeptik
    @_skeptik Рік тому

    i didn't fully catch the difference between cbow and skipgram in this explanation

  • @vionagetricahyo1268
    @vionagetricahyo1268 5 років тому

    hey can you share this code ?

  • @jatinsharma782
    @jatinsharma782 6 років тому

    Very Helpful 👍

  • @qaisgafer3562
    @qaisgafer3562 5 років тому

    Great

  • @shazadkhanfu
    @shazadkhanfu 2 роки тому

    charan kaha hai aapke?

  • @fabricesimodefo8113
    @fabricesimodefo8113 4 роки тому

    typo 5:25 the input words should change to "set" and "free"

  • @abdullahsahin4651
    @abdullahsahin4651 2 роки тому

    It was very confusing explanation. The slides are not consisted with the presenter's speech.