Word2Vec : Natural Language Processing

Поділитися
Вставка
  • Опубліковано 22 гру 2024

КОМЕНТАРІ •

  • @matthewson8917
    @matthewson8917 3 роки тому +15

    Finally, someone made a clear and concise introduction for Word2Vec! I admire you!

  • @revathik9225
    @revathik9225 10 місяців тому +3

    Great video. One thing to add: instead of always discarding the context vectors at the end, another strategy (mentioned in other videos/articles) is to concatenate or add the two vectors for a word.

  • @hahahaYL-h3x
    @hahahaYL-h3x 8 місяців тому +2

    You are a genius! You are able to explain abstract things well with only white board (no animation!)

  • @DC-tq1kh
    @DC-tq1kh 9 місяців тому +1

    Probably the best video explanation I watched. thank you.

  • @sefinehtesfa5189
    @sefinehtesfa5189 2 роки тому +1

    I appreciate your explanations.
    I was stuck on Word2Vec. However, you explainde this more than enough.
    Thank you so much!!!

  • @DennisRice-lh3nd
    @DennisRice-lh3nd Рік тому

    The best and most concise explanation of Word2Vec that I've seen so far. I probably need to go back and review gradient descent again, because updating the weights is still confusing.

  • @a00954926
    @a00954926 3 роки тому +4

    This is amazing!! I remember trying to understand this back when it was first published, and i failed so hard...thank you

  • @jett_royce
    @jett_royce 3 роки тому +4

    Great video. You mentioned that we discard the context vectors and take the main vectors as our final word embeddings. I just want to add that based on the literature, you can also add the main and context vectors, or concatenate them.

  • @drsandeepvm5622
    @drsandeepvm5622 2 роки тому +1

    Exceptionally simplified explanation. Thanks 😊

  • @yangwang9688
    @yangwang9688 3 роки тому +17

    Great explanation, it’s pure gold! Can you make a video in terms of hierarchical softmax? It confuses me for a long time.

  • @nobodyelse2230
    @nobodyelse2230 2 роки тому

    You're so good! Thank you very much for this explanation, my minds are so slear after it, magic!

  • @saikatroy3818
    @saikatroy3818 3 роки тому

    Explained in lucid manner. Nice video.

  • @vctorroferz
    @vctorroferz 6 місяців тому

    Incredible and amazing explanation! Thanks so much for such great content!

  • @SonalGore-q1v
    @SonalGore-q1v 9 місяців тому

    Cool....Made it very easy for me to understand about word2vec. Great explanation !!

  • @bharathtvadhoola715
    @bharathtvadhoola715 2 роки тому +1

    Awesome video! numerical example was particularly helpful. Cheers :)

  • @Recoils14
    @Recoils14 Рік тому

    This explanation is so well done! Thank you!

  • @purpleearth
    @purpleearth 8 місяців тому

    This is a superb explanation

  • @utuber1752
    @utuber1752 Рік тому

    EXCELLENT explanation!

  • @junekang2364
    @junekang2364 11 місяців тому

    Great video! Thank you for explaining this so clear.

  • @MikeKittelberger
    @MikeKittelberger 11 місяців тому

    Awesome explanation, you safe me a lot of time. Thank you! :)

  • @harshalingutla7318
    @harshalingutla7318 2 роки тому

    Brilliant explanation. To the point.

  • @dominicprior9844
    @dominicprior9844 Рік тому

    Wow, such a nice clear video! Many thanks!

  • @austossen
    @austossen 3 роки тому +5

    this is by far the best explanation of word2vec on youtube over any university lecture but one question. where and how are you getting your initial vector values in this example for V(like) and V(data)? can you also clarify the components of the vector? you have two columns/elements for each vector in the main vector and context vector.

    • @tellyrotsyourbrain
      @tellyrotsyourbrain 2 роки тому +2

      Exactly what I was wondering. Where do the initialisations of these vectors come from? I'm guessing they're initialised randomly, with the algorithm evolving the distribution into something that relates to the training data.

  • @arshadkazi4559
    @arshadkazi4559 2 роки тому +1

    Could you elaborate more on context and main embedding please? 6:00

  • @ebujak1
    @ebujak1 Рік тому +1

    Great Word2Vec video. Nice touch with blue for Main and red for Context. Working an example with numbers is also very good. Can we please have a follow up video (from ritvik "from the future" :) ) to do the UPDATE part of the loop? We know there are multiple ways to do this UPDATE, but just expound on the "simple" method of moving the vectors as you illustrated in 2D. Thanks.

  • @testimonies2914
    @testimonies2914 3 роки тому +2

    Nice ...thannk you so much

  • @gabrielemoro304
    @gabrielemoro304 7 місяців тому +1

    the dot product between V_like and V_data should be 0.4 and not 0.6 right? (min 8:27)

    • @KD4wg
      @KD4wg 7 місяців тому

      yes, the dot product is 0.4. But our score is the sigmoid of the dot product. And sigmoid(0.4) is roughly 0.598 ^^

  • @gnkk6002
    @gnkk6002 2 роки тому

    Good job as always👏

  • @zhiyili6707
    @zhiyili6707 2 роки тому

    Thank you for the video! Great content!

  • @FullStackAmigo
    @FullStackAmigo Рік тому

    I learned something, thanks a lot!

  • @Halo-uz9nd
    @Halo-uz9nd 3 роки тому +3

    Another fantastic video! The main/context embeddings kind of confused me but the ending really cleared it up. Curious to know if there is a deliberate way of choosing # of dimensions or if its simply trial and error. On a side note, will you be participating in the "66 days of data" challenge this July?

  • @HiteshKumar-bk2od
    @HiteshKumar-bk2od 3 роки тому +3

    Can you please make a video on transformers, attention and Bert models in detail . It will be in Continuation with word vectors.

  • @kostjamarschke4613
    @kostjamarschke4613 2 роки тому

    Phenomenal stuff!

    • @kostjamarschke4613
      @kostjamarschke4613 2 роки тому

      Honestly phenomenal. You covered 80% of a 90-minute Masters-level ML lecture in 13 minutes and made it very easy to understand.

  • @limkangwei6339
    @limkangwei6339 2 місяці тому

    This is fascinating!!! Question: How do we get the initial vectors before even starting the for loop?

  • @hameddadgour
    @hameddadgour 2 роки тому

    Great presentation!

  • @mmenjic
    @mmenjic 3 роки тому +1

    And how do we distinguish between 2 same words in this case "data" if we have larger text where data is next to science but it is also close to other word or words for example data processing, data mining, data validation, data.... data..... everything, is it the case that word data is "closer" to word science in general than it is to word processing or there is some other mechanism for this ?

  • @michaelm358
    @michaelm358 Рік тому

    Outsanding!

  • @muhammadal-qurishi7110
    @muhammadal-qurishi7110 3 роки тому +2

    You are always great in your explanations
    Can you explain CRF please

  • @pampagrimaldi8584
    @pampagrimaldi8584 Рік тому

    great explanation! thank you!

  • @vincentouwendijk3746
    @vincentouwendijk3746 9 місяців тому

    Great video!

  • @0815-j3s
    @0815-j3s 8 місяців тому

    Simply since the distances are invariant under orthogonal transformations of the space "embeddings" (by the way: Not in the mathematical sense) are not unique. But they also depend on the prupose of the model.

  • @priyasah6123
    @priyasah6123 11 місяців тому

    How to calculate score ? We need to take dot product of what exactly with main and context ?

  • @jagadeeshwaran1512
    @jagadeeshwaran1512 7 місяців тому

    How does the Main embedding is calculated?. How is the vector defined?

  • @houyao2147
    @houyao2147 3 роки тому

    very intuitive!

  • @nobodyelse2230
    @nobodyelse2230 2 роки тому

    Hello again! After a couple of days of studying another materials, I realized that I don't understand where the formulas for the score and the error come from, I don't see them in the books I read (and I haven't seen this approach with labels yet either). Are there any papers or books where I can find them and the prove that they work?

  • @bartoszko4028
    @bartoszko4028 Рік тому

    Well explained, but doesn't sigmoid function give values from 0 to 1? Then maybe it should be tanh activation function?

    • @ebujak1
      @ebujak1 Рік тому

      Score needs to be positive since the error needs to be opposite (error = label - score). tanh is negative and positive ... so hard to interpret error.

  • @VincentVanZgegh
    @VincentVanZgegh Рік тому

    Great video ! Thx

  • @moatasem444
    @moatasem444 Рік тому

    There is a prepared embedding?

  • @edphi
    @edphi Рік тому

    Very awesome

  • @sa-vx5vi
    @sa-vx5vi 2 роки тому

    Thanks a lot

  • @oraz.
    @oraz. 2 роки тому +1

    What determines the dimension of the word vectors? Edit I guess it's just an engineering decision.

  • @golnoushghiasi7698
    @golnoushghiasi7698 2 роки тому

    Can you explain some more NLP models such as Bert, Fasttext and transformers?

  • @lsacy8347
    @lsacy8347 2 роки тому

    why is this word2vec so different from "conventional" word2vec where you use a neural network and bag of words to calculate the weights matrix? ok, my bad, just realized you talked about neural network update method towards the end.

  • @mosca-tse-tse
    @mosca-tse-tse 3 роки тому +1

    So how does it happen than king - man + woman = queen, a very common selling example of wod2vec?

    • @muhammadal-qurishi7110
      @muhammadal-qurishi7110 3 роки тому +1

      check this video and you will have clear understanding ua-cam.com/video/4-QoMdSqG_I/v-deo.html

    • @mosca-tse-tse
      @mosca-tse-tse 3 роки тому

      @@muhammadal-qurishi7110 cool 👍🏻 thanks!

  • @agamchug595
    @agamchug595 2 роки тому

    How is the initial size of the vectors determined? As you mentioned that traditionally there may be vectors with 50 dimensions and your example has used 2 to ease understanding.

  • @bilalsidiqi9992
    @bilalsidiqi9992 2 роки тому

    Could you please implement some NLP models in pytorch or tensorflow?

  • @CarlJohnson-jj9ic
    @CarlJohnson-jj9ic 2 роки тому

    Is chloroform FDA approved for a mechanics lean on a judgement?

  • @sachinrathi7814
    @sachinrathi7814 2 роки тому

    Can someone will explain where those 2 numeric values (vector representation) for like word, -.2 and -1 comes from ?
    Word2vec is used to create numeric representation of words in vector form or create vector in such a way that word which are close in documents are also close in vectors representation as well ?

    • @goumuk
      @goumuk 2 роки тому +1

      initially the values are randomly set. after each iteration of computation, the values keep getting updated.

  • @kundansaha4877
    @kundansaha4877 2 роки тому

    please make a video how spacy works

  • @vyvu443
    @vyvu443 8 місяців тому

    Ritvik... can you do NLP, word embeddings with GloVe and FastText :D :D :D Thank you in advance!

  • @kevinscaria
    @kevinscaria Рік тому

    Wow

  • @RonLWilson
    @RonLWilson 2 роки тому

    Just FYI, I just made and uploaded a UA-cam video where I used bits of your video here as a use case to illustrate a graphical ontology language that I am calling UniML, Universal Modeling L (not to be confused with UML, Unified modeling Language).
    While things like neural nets map transformation or functions (f: X -> Y) UniML attempts to model more than that and model the thing itself, including any such transformations as an ontology model but not using just symbols such as does ontology languages such as OWL or RDF but graphically so that graphically depicts the under lying data structures.
    Here is a link to my video
    ua-cam.com/video/bioz226CcWY/v-deo.html

  • @gagangayari5981
    @gagangayari5981 2 роки тому

    Perfect explanation. How would doc2vec fit along the same lines with the algorithm you mentioned ? Can you please briefly tell ? @ritvikmath

  • @shakeelm5339
    @shakeelm5339 11 місяців тому

    I have no clue what the heck he talked about.