Word2Vec - Skipgram and CBOW

Поделиться
HTML-код
  • Опубликовано: 29 янв 2025

Комментарии • 136

  • @rma1563
    @rma1563 10 месяцев назад +6

    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 года назад +8

    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 года назад +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 года назад +13

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

  • @fabricesimodefo8113
    @fabricesimodefo8113 4 года назад +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 года назад +2

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

  • @subhamprasad6808
    @subhamprasad6808 3 года назад

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

  • @sheshagirigh
    @sheshagirigh 5 лет назад +10

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

  • @Amf313
    @Amf313 2 года назад +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 9 месяцев назад

    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!

  • @thunder-v8h
    @thunder-v8h 4 года назад +2

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

  • @chihiroa1045
    @chihiroa1045 Год назад

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

  • @maqboolurrahimkhan
    @maqboolurrahimkhan 3 года назад

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

  • @noobesthost
    @noobesthost 4 года назад

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

  • @tylerlozano152
    @tylerlozano152 5 лет назад +6

    Thank you for the thorough, simple explanation.

  • @pushkarmandot4426
    @pushkarmandot4426 5 лет назад +5

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

  • @MuhammadQasim-f7d
    @MuhammadQasim-f7d 2 месяца назад

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

  • @anujlahoty8022
    @anujlahoty8022 Год назад

    Simple and eloquent explanation.

  • @rainoorosmansaputratampubo2213
    @rainoorosmansaputratampubo2213 4 года назад

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

  • @bryancamilo5139
    @bryancamilo5139 11 месяцев назад

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

  • @FTLC
    @FTLC Год назад

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

  • @ajinkyajoshi2308
    @ajinkyajoshi2308 2 года назад

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

  • @mohajeramir
    @mohajeramir 4 года назад

    this is the best explanation I have found. thank you

    • @TheSemicolon
      @TheSemicolon  4 года назад

      Glad you found it useful, do share the word 🙂

  • @MrStudent1978
    @MrStudent1978 4 года назад

    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....

  • @jusjosef
    @jusjosef 4 года назад

    Very simple, to the point explanation. Beautiful!

  • @Ib-nt8nk
    @Ib-nt8nk 3 года назад

    Good work! Nicely explained.

  • @aravindaraman8667
    @aravindaraman8667 3 года назад

    Amazing explanation! Thanks a lot

  • @nithin5238
    @nithin5238 5 лет назад

    Very clear explanation man.. you deserve slow claps

  • @johncompassion9054
    @johncompassion9054 9 месяцев назад

    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.

  • @jamesmina7258
    @jamesmina7258 6 месяцев назад

    Thank you. I learned a lot from your video.

  • @Zinghere
    @Zinghere 2 года назад

    Great explanation!

  • @befesa1
    @befesa1 8 месяцев назад

    Thank you! Really good explanation:)

  • @carlrobinson2926
    @carlrobinson2926 6 лет назад

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

  • @gouripeddivenkataasrithbha5148
    @gouripeddivenkataasrithbha5148 4 года назад

    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 года назад

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

  • @varunjindal1520
    @varunjindal1520 4 года назад

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

    • @TheSemicolon
      @TheSemicolon  4 года назад

      Glad you found it useful, do share the word 🙂

  • @keno2055
    @keno2055 2 года назад

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

  • @satyarajadasara9000
    @satyarajadasara9000 4 года назад

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

  • @vid_sh_itsme4340
    @vid_sh_itsme4340 6 месяцев назад

    is hierarchical softmax used in this?

  • @hardikajmani5088
    @hardikajmani5088 5 лет назад

    Very well explained

  • @OorakanaGleb
    @OorakanaGleb 5 лет назад

    Awesome explanation. Thanks!

  • @absoluteanagha
    @absoluteanagha 3 года назад

    Love this! Such a great explanation!

  • @AdityaPatilR
    @AdityaPatilR 4 года назад

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

  • @bloodzitup
    @bloodzitup 5 лет назад

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

  • @impracticaldev
    @impracticaldev 2 года назад

    You earned a subsciption. Good luck!

  • @theunknown2090
    @theunknown2090 6 лет назад +2

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

  • @ankursri21
    @ankursri21 5 лет назад

    Thank you.. very well explained in shorter time.

  • @coolbowties394
    @coolbowties394 4 года назад

    Thanks so much for this thorough explanation!

  • @ashwinrameshbabu2418
    @ashwinrameshbabu2418 4 года назад

    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?

  • @Hellow_._
    @Hellow_._ Год назад

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

  • @avanianchalia
    @avanianchalia Месяц назад

    Insightful!

  • @ogsconnect1312
    @ogsconnect1312 5 лет назад

    I cannot say anything but excellent. Thank you

  • @amirmasoud_iravani
    @amirmasoud_iravani День назад

    great😍 thx a million

  • @hashinitheldeniya1347
    @hashinitheldeniya1347 4 года назад

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

  • @057ahmadhilmand6
    @057ahmadhilmand6 Год назад

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

  • @himanshusrihsk4302
    @himanshusrihsk4302 5 лет назад

    Really very useful

  • @anindyavedant801
    @anindyavedant801 5 лет назад +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

  • @md.prantohasan9630
    @md.prantohasan9630 5 лет назад +1

    Excellent explanation in a very short time. Take

  • @shikharkesarwani9051
    @shikharkesarwani9051 5 лет назад +9

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

  • @MehdiMirzapour
    @MehdiMirzapour 5 лет назад

    Thanks. It is really a brilliant explanation!

  • @fahdciwan8709
    @fahdciwan8709 4 года назад

    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 года назад

      Basically the weight matrix is the word embedding

  • @tobiascornille
    @tobiascornille 4 года назад

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

  • @romanm7530
    @romanm7530 3 года назад

    Диктор просто огонь!

  • @iliasp4275
    @iliasp4275 4 года назад

    thank you , The Semicolon.

  • @parthpatel3900
    @parthpatel3900 5 лет назад

    Wonderful video

  • @naveenkinnal5413
    @naveenkinnal5413 4 года назад

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

    • @TheSemicolon
      @TheSemicolon  4 года назад

      No, sliding window can be of any size.

  • @TheEducationWorldUS
    @TheEducationWorldUS 4 года назад

    nice explanation

  • @nazrulhassan6310
    @nazrulhassan6310 3 года назад

    fabulous explanation but I need to do some more digging

  • @mohajeramir
    @mohajeramir 4 года назад

    this was excellent. Thank you

  • @qingyangluo7085
    @qingyangluo7085 4 года назад

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

    • @TheSemicolon
      @TheSemicolon  4 года назад

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

    • @qingyangluo7085
      @qingyangluo7085 4 года назад

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

  • @juanpablo87t
    @juanpablo87t 3 года назад

    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?

  • @mohitagarwal437
    @mohitagarwal437 3 года назад +1

    Best bhai aapne pura data science kar rakha hai kya ?

  • @muhammedhassen4354
    @muhammedhassen4354 5 лет назад

    easy way explanation gr8

  • @Mr.AIFella
    @Mr.AIFella Год назад

    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?

  • @hadrianarodriguez6666
    @hadrianarodriguez6666 4 года назад

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

    • @TheSemicolon
      @TheSemicolon  4 года назад

      you may want to append them may be ?

  • @gauharahmad2643
    @gauharahmad2643 5 лет назад

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

  • @prathimads2876
    @prathimads2876 6 лет назад

    Thank you so much Sir...

  • @dhruvagarwal4477
    @dhruvagarwal4477 4 года назад

    What is the meaning of vector size?

  • @imanbio
    @imanbio 4 года назад

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

  • @tumul1474
    @tumul1474 5 лет назад +1

    awesome !!

  • @aliqais4896
    @aliqais4896 5 лет назад

    thank you very much

  • @pranabsarkar
    @pranabsarkar 4 года назад

    Thanks a lot!

  • @randomforrest9251
    @randomforrest9251 3 года назад

    nice slides!

  • @alialsaffar6090
    @alialsaffar6090 6 лет назад +1

    This was enlightening. Thank you!

  • @ms10596
    @ms10596 5 лет назад

    So helpful

  • @josephselwan1652
    @josephselwan1652 3 года назад

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

  • @BrunoCPunto
    @BrunoCPunto 3 года назад

    Awesome

  • @Simply-Charm
    @Simply-Charm 4 года назад

    Thank you

  • @sunjitrana374
    @sunjitrana374 5 лет назад

    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.

  • @arnav3674
    @arnav3674 9 месяцев назад

    Good !

  • @MultiAkshay009
    @MultiAkshay009 6 лет назад

    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 лет назад

      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.

  • @DangNguyen-xx3zi
    @DangNguyen-xx3zi 4 года назад

    Appreciate the work put into this video, thank you!

  • @prajitvaghmaria3669
    @prajitvaghmaria3669 6 лет назад

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

  • @theacid1
    @theacid1 4 года назад +1

    Thank you. My prof is unable to explain it.

  • @saikiran-mi3jc
    @saikiran-mi3jc 3 года назад

    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.

  • @abdallahessam4671
    @abdallahessam4671 2 года назад

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

  • @vionagetricahyo1268
    @vionagetricahyo1268 5 лет назад

    hey can you share this code ?

  • @hs_harsh
    @hs_harsh 5 лет назад

    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!

  • @_skeptik
    @_skeptik Год назад

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

  • @jatinsharma782
    @jatinsharma782 6 лет назад

    Very Helpful 👍

  • @fabricesimodefo8113
    @fabricesimodefo8113 4 года назад

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

  • @qaisgafer3562
    @qaisgafer3562 5 лет назад

    Great