Vectoring Words (Word Embeddings) - Computerphile

Поділитися
Вставка
  • Опубліковано 25 лис 2024

КОМЕНТАРІ • 416

  • @VladVladislav790
    @VladVladislav790 5 років тому +367

    "Not in this data set" is my new favorite comeback oneliner

    • @MrAmgadHasan
      @MrAmgadHasan Рік тому

      It's similar to "not in this timeline" that we hear a lot in time-travel scifi

    • @Jason-wm5qe
      @Jason-wm5qe Рік тому +1

      😂

  • @wohdinhel
    @wohdinhel 5 років тому +1132

    “What does the fox say?”
    “Don’t they go ‘ring ding ding’?”
    “Not in this dataset”

    •  5 років тому +52

      Train the same algorithm on songs instead of news articles and I figure you could get some really interesting results as well. Songs work on feelings and that should change the connections between the words as well - I bet the technology can be used to tell a lot about the perspective people take on things as well.

    • @argenteus8314
      @argenteus8314 5 років тому +21

      @ Songs also use specific rhythmic structures; assuming most of your data was popular music, I bet that there'd be a strong bias for word sequences that can fit nicely into a 4/4 time signature, and maybe even some consistent rhyming structures.

    • @killedbyLife
      @killedbyLife 5 років тому +1

      @ Train it with only lyrics from Manowar!

    • @ruben307
      @ruben307 5 років тому +3

      @ I wonder how strong Rhymes would show up in that dataset.

    •  5 років тому

      @@killedbyLife That's odd - I listen to Manowar regularly. Nice pick. 😉

  • @kurodashinkei
    @kurodashinkei 5 років тому +320

    Tomorrow's headline:
    "Science proves fox says 'Phoebe'"

  • @rich1051414
    @rich1051414 5 років тому +165

    This thing would ace the analogy section of the SAT.
    Apple is to tree as grape is to ______.
    model.most_similar_cosul(positive['tree', 'grape'], negative['apple']) = "vine"

  • @Alche_mist
    @Alche_mist 5 років тому +282

    Fun points: A lot of the Word2vec concepts come from Tomáš Mikolov, a Czech scientist at Google. The Czech part is kinda important here - Czech, as a Slavic language, is very flective - you have a lot of different forms for a single word, dependent on its surroundings in a sentence. In some interview I read (that was in Czech and in a paid online newspaper, so I can't give a link), he mentioned that this inspired him a lot - you can see the words clustering by their grammatical properties when running on a Czech dataset and it's easier to reason about such changes when a significant portion of them is exposed visibly in the language itself (and learned as a child in school, because some basic parts of it are needed in order to write correctly).

    • @JDesrosiers
      @JDesrosiers Рік тому +8

      very interesting

    • @afriedrich1452
      @afriedrich1452 Рік тому +8

      I keep wondering if I was the one who gave the inventor of Word2vec the idea of vectoring words 15 years ago. Probably not.

    • @notthedroidsyourelookingfo4026
      @notthedroidsyourelookingfo4026 Рік тому +4

      Now I wonder what would've happened if it had been a Chinese, where you don't have that at all!

    • @StoutProper
      @StoutProper Рік тому +1

      Wonder how this works with Japanese? Their token spaces must be much bigger and more complex

    • @newbie8051
      @newbie8051 Рік тому +1

      Technically you can share the link to the newspaper

  • @xario2007
    @xario2007 5 років тому +309

    Okay, that was amazing. "London + Japan - England = Tokyo"

    • @yshwgth
      @yshwgth 5 років тому +11

      That needs to be a web site

    • @cheaterman49
      @cheaterman49 5 років тому +67

      More impressed by Santa + pig - oink = "ho ho ho"

    • @VoxAcies
      @VoxAcies 5 років тому +28

      This blew my mind. Doing math with meaning is amazing.

    • @erikbrendel3217
      @erikbrendel3217 5 років тому +9

      you mean Toyko!

    • @Dojan5
      @Dojan5 5 років тому +16

      I was actually expecting New York when they added America. As a child I always thought New York was the capital of the U.S., I was at least around eight when I learned that it wasn't. Similarly, when people talk of Australia's cities, Canberra is rarely spoken of, but Sydney comes up a lot.

  • @Cr42yguy
    @Cr42yguy 5 років тому +110

    EXTRA BITS NEEDED!

  • @bluecobra95
    @bluecobra95 5 років тому +274

    'fox' + 'says' = 'Phoebe' may be from newspapers quoting English actress Phoebe Fox

    • @skepticmoderate5790
      @skepticmoderate5790 5 років тому +20

      Wow what a pull.

    • @rainbowevil
      @rainbowevil 3 роки тому +5

      It was given ‘oink’ minus ‘pig’ plus ‘fox’ though, not fox + says. So we’d expect to see the same results as for cow & cat etc. of it “understanding” that we’re looking at the noises that the animals make. Obviously it’s not understanding, just an encoding of how those words appear near each other, but we end up with something remarkably similar to understanding.

  • @buzz092
    @buzz092 5 років тому +156

    Always love to see Rob Miles here!

    • @RobertMilesAI
      @RobertMilesAI 5 років тому +40

    • @yondaime500
      @yondaime500 5 років тому +1

      Even when the video doesn't have that "AAAHH" quality to it.

  • @Chayat0freak
    @Chayat0freak 5 років тому +284

    I did this for my final project in my bsc. Its amazing. I found cider - apples + grapes = wine. My project attempted to use these relationships to build simulated societies and stories.

    • @Games-mw1wd
      @Games-mw1wd 5 років тому +21

      would you be willing to share a link? This seems really interesting.

    • @TOASTEngineer
      @TOASTEngineer 5 років тому +7

      Yeah, that sounds right up my alley, how well did it work

    • @ZoranRavic
      @ZoranRavic 4 роки тому +24

      Dammit Dean, you can't bait people with this kind of a project idea and not tell us how it went

    • @KnakuanaRka
      @KnakuanaRka 4 роки тому +2

      You want to give some info as to how that went?

    • @blasttrash
      @blasttrash 2 роки тому +1

      you are lying you did not do it. if you did, then paste the source(paper or code).
      - cunningham

  • @panda4247
    @panda4247 5 років тому +111

    I like this guy and his long sentences. It's nice to see somebody who can muster a coherent sentence of that length.
    So, if you run this (it's absurdly simple, right), but if you run this on a large enough data set and give it enough compute to actually perform really well, it ends up giving you for each word a vector (that's of length however many units you have in your hidden layer), for which the nearby-ness of those vectors expresses something meaningful about how similar the contexts are that those words appear in, and our assumption is that words that appear in similar contexts are similar words.

    • @thesecondislander
      @thesecondislander Рік тому +35

      His neural network has a very large context, evidently ;)

    • @MrAmgadHasan
      @MrAmgadHasan Рік тому +2

      Imagine a conversation between him and D Trump.

  • @alexisxander817
    @alexisxander817 3 роки тому +223

    I am in love with this man's explanation! makes it so intuitive. I have a special respect for folks who can make a complex piece of science/math/computer_science into an abstract piece of art. RESPECT!

    • @nidavis
      @nidavis 2 роки тому +9

      "it's the friends you make along the way" lol

    • @sgttomas
      @sgttomas Рік тому +2

      I was just thinking this and came to the comments…. Yup. Mr Miles is terrific. 🎉

    • @webgpu
      @webgpu Рік тому

      "complex" ? 🙂

    • @Commiehunter12
      @Commiehunter12 Рік тому

      He's Twerp. He's afraid to talk about X Y and XX Chromosomes and how we express them in language. shame on you

    • @subject8332
      @subject8332 Рік тому +3

      @@Commiehunter12 No, he just didn't want to trigger the priesthood in a video about word embeddings but looks like he wasn't careful enough.

  • @wolfbd5950
    @wolfbd5950 5 років тому +64

    This was weirdly fascinating to me. I'm generally interested by most of the Computerphile videos, but this one really snagged something in my brain. I've got this odd combination of satisfaction and "Wait, really? That works?! Oh, wow!"

  • @nemanjajerinic6141
    @nemanjajerinic6141 11 місяців тому +8

    Today, vector databases are a revolution to AI models. This man was way ahead of time.

  • @veggiet2009
    @veggiet2009 5 років тому +86

    Foxes do chitter!
    But primarily they say "Phoebe"

  • @adamsvoboda7717
    @adamsvoboda7717 5 років тому +75

    Meanwhile in 2030:
    "human" + "oink oink" - "pig" = "pls let me go skynet"

  • @Verrisin
    @Verrisin 5 років тому +6

    floats: some of the real numbers
    - Best description and explanation ever! - It encompasses all the problems and everything....

    • @RobertMilesAI
      @RobertMilesAI 4 роки тому +9

      "A tastefully curated selection of the real numbers"

  • @Alkis05
    @Alkis05 4 роки тому +17

    This is basically node embedding from graph neural networks. Each sentence you use to train the it can be seen as a random walk in the graph that relates each world with each other. The number of words in the sentence can be seem as how long you walk from the node. Besides "word-vector arithmetics", one thing interesting to see would be to use this data to generate a graph of all the words and how they relate to each other. Than you could do network analysis with it, see for example, how many clusters of words and figure out what is their labels. Or label a few of them and let the graph try to predict the rest of them.
    Another interesting thing would be to try to embed sentences based on the embedding of words. For that you would get a sentence and train a function that maps points in the word space to points in the sentence space, by aggregating the word points some how. That way you could compare sentences that are close together. Then you can make sentences-vector arithmetics.
    This actually sounds like a cool project. I think I'm gonna give it a try.

  • @SeanSuggs
    @SeanSuggs 6 місяців тому +1

    Rob Miles and computerphile thank you... IDK why youtube gave this gem back to me today (probably for my insesent searching for the latest LLM news these days) but I am greatful to you even more now than I was 4yrs ago... Thank you

  • @joshuar3702
    @joshuar3702 5 років тому +40

    I'm a man of simple tastes. I see Rob Miles, I press the like button.

  • @tapanbasak1453
    @tapanbasak1453 11 місяців тому +1

    This page blows my mind. It takes you through the journey of thinking.

  • @kal9001
    @kal9001 5 років тому +87

    Rather than biggest city, it seems obvious it would be the most written about city, which may or may not be the same thing.

    • @packered
      @packered 5 років тому +12

      Yeah, I was going to say most famous cities. Still a very cool relationship

    • @oldvlognewtricks
      @oldvlognewtricks 5 років тому +12

      Would be interested by the opposite approach: ‘Washington D.C. - America + Australia = Canberra’

    • @Okradoma
      @Okradoma 5 років тому

      Toby Same here...
      I’m surprised they didn’t run that,

    • @tolep
      @tolep 3 роки тому

      Stock markets

  • @crystalsoulslayer
    @crystalsoulslayer Рік тому +1

    It makes so much more sense to represent words numerically rather than as collections of characters. That may be the way we write them, but the characters are just loose hints at pronunciation, which the model probably doesn't care about for meaning. And what would happen if a language model that relied on characters tried to learn a language that doesn't use that system of writing? Fascinating stuff.

  • @PerMortensen
    @PerMortensen 5 років тому +23

    Wow, that is mindblowing.

  • @muddi900
    @muddi900 5 років тому +99

    'What does it mean for two words to be similar?'
    That is a philosophy lesson I am not ready for bro

    • @williamromero-auila7129
      @williamromero-auila7129 5 років тому +6

      Breau

    • @_adi_dev_
      @_adi_dev_ 5 років тому +4

      How dare you assume my words meaning, don't you know its the current era

    • @cerebralm
      @cerebralm 5 років тому +9

      that's kind of the great thing about computer science... you can take philosophical waffling and actually TEST it

    • @youteubakount4449
      @youteubakount4449 5 років тому

      I'm not your bro, pal

    • @carlosemiliano00
      @carlosemiliano00 4 роки тому +4

      @@cerebralm "Computer science is the continuation of logic
      by other means"

  • @Sk4lli
    @Sk4lli 5 років тому +8

    This was soooo interesting to me. I never dug deeper in how these networks work. But so many "Oh! That's how it is!". When I watched the video about GPT-2 and you he said that all the connections are just statistics, I just noted that internally as interesting and "makes sense" but didn't really get it. But with this video it clicked!
    So many interesting things, so thanks a lot for that. I love these videos.
    And seeing the math that can be done with these vectors is amazing! Wish I could like this more than once.

  • @vindolanda6974
    @vindolanda6974 4 місяці тому

    I love how this video seems to have time travelled from 1979 - the austere painted brick classroom, the shirt, the hair and beard, even the thoughtful and articulate manner seem to come from another time.

  • @b33thr33kay
    @b33thr33kay Рік тому +17

    You really have a way with words, Rob. Please never stop what you do. ❤️

  • @arsnakehert
    @arsnakehert Рік тому

    Love how you guys are just having fun with the model by the end

  • @LeoStaley
    @LeoStaley 5 років тому +21

    I'm a simple man. I see Rob Miles, I click.

    • @koerel
      @koerel 4 роки тому

      I could listen to him all day!

  • @mynamesnotsteve
    @mynamesnotsteve 3 роки тому +4

    I'm surprised that there's been no mention of Rob's cufflinks in the comments for well over a year after upload

  • @abdullahyahya2471
    @abdullahyahya2471 Рік тому +1

    Mind blown, Thanks for the easy explanation. So calm and composed.

  • @JanaiaC
    @JanaiaC Місяць тому +1

    Excellent presentation

  • @MakkusuOtaku
    @MakkusuOtaku 5 років тому +23

    Word embedding is my favorite pass-time.

  • @cheeyuanng853
    @cheeyuanng853 2 роки тому

    This gotta be one of the best intuitive explanation of word2vec.

  • @distrologic2925
    @distrologic2925 4 роки тому +10

    I love that I have been thinking about modelling natural language for some time now, and this video basically confirms my way of heading. I have never heard of word embedding, but its exactly what I was looking for. Thank you computerphile and youtube!

  • @tridunghuynh5573
    @tridunghuynh5573 3 роки тому +1

    I love the way he's discussing complicated topics. Thank you very much

  • @Verrisin
    @Verrisin 5 років тому +89

    Man, ... when AI will realize we can only imagine 3 dimensions, it will be so puzzled how we can do anything at all...

    • @overloader7900
      @overloader7900 4 роки тому +12

      Actually 2 spacial visual dimension with projection...
      Then we have time, sounds, smells...

    • @Democracy_Manifest
      @Democracy_Manifest Рік тому

      The amount of neurons is more important than the experienced dimensions.

  • @kamandshayegan4824
    @kamandshayegan4824 Рік тому

    I am amazed and in love with his explanations. I just understand it clearly, you know.

  • @WondrousHello
    @WondrousHello Рік тому +13

    This has suddenly become massively relevant 😅

  • @SpaceChicken
    @SpaceChicken Рік тому +5

    Phenomenal talk. Surprisingly compelling given the density of the topic.
    I really do hope they let this man out of prison one day.

  • @superjugy
    @superjugy 5 років тому +4

    OMG that ending. Love Robert's videos!

  • @danielroder830
    @danielroder830 5 років тому +2

    You could make a game with that, some kind of scrabble with random words, add and substract words to get other words. Maybe with the goal to get long words or specific words or get shortest or longest distance from a specific word.

  • @tommyhuffman7499
    @tommyhuffman7499 Рік тому +1

    This is by far the best video I've seen on Machine Learning. So cool!!!

  • @patricke1362
    @patricke1362 9 місяців тому

    super nice style of speaking, voice and phrasing. Good work !

  • @channagirijagadish1201
    @channagirijagadish1201 2 роки тому +2

    Very well done. I love the explanation. He obviously has deep insight to explain it so very well. Thanks.

  • @funkysagancat3295
    @funkysagancat3295 4 місяці тому

    Awesome that with ChatGPT and stable diffusion this video got super relevant

  • @bruhe_moment
    @bruhe_moment 5 років тому +2

    Very cool! I didn't know we could do word association to this degree.

  • @datasciyinfo5133
    @datasciyinfo5133 Рік тому +1

    Thanks for a great explanation of word embeddings. Sometimes I need a review. I think I understand it, then after looking at the abstract, n-dimensional embedding space in ChatGPT and Variational Autoencoders, I forget about the basic word embeddings. At least it’s a simple 300-number vector per word, that describes most of the highest frequency neighboring words.

    • @michaelcharlesthearchangel
      @michaelcharlesthearchangel Рік тому

      Me too. I loved the review after looking how GPT4 and its code/autoencoder-set looks under the hood. I also had to investigate the keywords being used like "token" when we think about multi vector signifiers and the polysemiology of glyphic memorization made by these massive AI databases.
      Parameters for terms, words went from 300 to 300,000 to 300,000,000 to 1.5 trillion to ♾ infinite. Meaning: Pinecone and those who've reached infinite parameters have created the portal to a true self-learning operating system, self-aware AI.

  • @helmutzollner5496
    @helmutzollner5496 Рік тому +1

    Very interesting. Would like to see more about these word vectors and how to use them.

  • @Nagria2112
    @Nagria2112 5 років тому +6

    Rob Miles is back :D

  • @Great.Milenko
    @Great.Milenko Рік тому +1

    I kinda overlooked the importance of this video when it was released 3 yrs ago. not its basically the explanaition of how chatGPT does its thing... but with more data.

  • @theepicsnail
    @theepicsnail 5 років тому +20

    I'm realllly curious about the basis vectors in this. What's the closest few words to etc..

    • @Guztav1337
      @Guztav1337 5 років тому +2

      That. Now I'm really curious.

    • @yugioh8810
      @yugioh8810 5 років тому

      I don't think that such reprenstation captures the distance information at all to begin with. The *closest* word is it has a distance of 1, (hamming distance in this case, I claim that each flipped bit counts as 1 hamming distance), but is not a word at all. Whereas in a vector-encoded representation since the words are mapped to a *vector space* then the closeness-farness of two vectors are conveyed in that representation. information representation if a fabulous topic I don't think I understand it yet. Information theory may help us understand information and information representation.

    • @Guztav1337
      @Guztav1337 5 років тому +7

      @worthy null , wtf are you on about? Nobody said anything about Hamming distance.
      He asked: what few words are the closest to the basis vectors [in euclidean distance] in that vector space.

    • @LEZAKKAZ
      @LEZAKKAZ 5 років тому +3

      I see where youre going with your analogy, but embeddings generally dont work like that. At first all the words are randomly given a random vector and then those vectors change throughout the training process. So the words you're looking for would be meaningless in this case. If you're looking for the centroid word(words that appear in the center of the embeddings) then that would be words that have very broad contexts such as "the".

    • @theepicsnail
      @theepicsnail 5 років тому

      @Gerben van Straaten something that might be cute would be defining some human meaningful basis vectors then rotating/scaling the points to fit them. Then see what the remaining basises are. You're definitely right that they would not be human meaningful out of the box though

  • @abhisheksarkar_neo
    @abhisheksarkar_neo 2 місяці тому

    4 years ago if only we had the vision to understand that this is actually a multi billion dollar, world changing idea!

  • @debayanpal8107
    @debayanpal8107 7 місяців тому

    best explanation about word embedding

  • @peabnuts123
    @peabnuts123 5 років тому

    16:20 Rob loves it, he's so excited by it 😄

  • @RazorbackPT
    @RazorbackPT 5 років тому +48

    I would suspect that this has to be very similar to how our own brains interpret languange, but then again evolution has a tendency to go about solving problems in very strange and inefficient ways.

    • @maxid87
      @maxid87 5 років тому +1

      Do you have examples? I am really curious - so far I always assumed nature does it the most efficient way possible.

    • @wkingston1248
      @wkingston1248 5 років тому +22

      @@maxid87 mammals have a nerve that goes from the brain to the throat, but due to changes in mammals it always goes under a vien in the heart then back up to the throat. This is so extreme that on a giraffe the nerve is like 9 feet long or something. In general evolution does a bad job at remmoving unnecessary features.

    • @Bellenchia
      @Bellenchia 5 років тому

      Clever Hans

    • @maxid87
      @maxid87 5 років тому

      @@wkingston1248 how do you know that this is inefficient? Might seem like that at first glance but maybe there is some deeper reason for it? Are there actual papers on this topic that answer the question?

    • @cmilkau
      @cmilkau 5 років тому

      I doubt there is a lot of evolution at play in human language processing. It seems reasonable to assume that association (cat~dog) and decomposition (Tokyo = japanese + city) play an important role.

  • @kenkiarie
    @kenkiarie 5 років тому +1

    This is very impressive. This is actually amazing.

  • @lonephantom09
    @lonephantom09 4 роки тому +1

    Beautifully simple explanation! Resplendent!

  • @MrSigmaSharp
    @MrSigmaSharp 5 років тому +3

    Oh yes, explaination and a concrete example

  • @Sanders4069
    @Sanders4069 8 місяців тому

    So glad they allow this prisoner a conjugal visit to discuss these topics!

  • @Razzha
    @Razzha 5 років тому +3

    Mind blown, thank you very much for this explanation!

  • @Noxeus1996
    @Noxeus1996 5 років тому

    This video really deserves more views.

  • @JamieDodgerification
    @JamieDodgerification 5 років тому +23

    Would it be possible for Rob to share his colab notebook / code with us so we can play around with the model for ourselves? :D

    • @jeffreymiller2801
      @jeffreymiller2801 5 років тому

      I'm pretty sure it's just the standard model that comes with gensim

    • @steefvanwinkel
      @steefvanwinkel 5 років тому

      See bdot02's comment above

  • @rafaelzarategalvez6728
    @rafaelzarategalvez6728 5 років тому +2

    It'd have been nice to hear about the research craze around more sophisticated approaches to NLP. It's hard to keep up with the amount of publications lately related to achieving "state-of-the-art" models using GLUE's benchmark.

  • @endogeneticgenetics
    @endogeneticgenetics Рік тому +1

    Would love sample code in cases like this where there’s a Jupyter notebook already laying about!

  • @nonchip
    @nonchip 5 років тому +5

    3:00 pretty sure that graphic should've been just 2 points on the same line, given what he said a few sentences before that.

    • @panda4247
      @panda4247 5 років тому

      Yep, if the mapping of images is just taking the values each pixel and then making N-dimensional vector (where N is number of pixels), then the picture with more brightness would be the on the same line (if solid black pixels were still solid black, depending on your brightness filter applied).

  • @4.0.4
    @4.0.4 5 років тому +7

    I never thought the difference between "man" and "woman" could be so intertwined in a language! I can imagine it would make some people uneasy.

  • @Pasan34
    @Pasan34 2 роки тому +1

    Put 'politician' instead of Santa in the last example. Buy you a beer if it comes out as 'bleating'.

  • @taneliharkonen2463
    @taneliharkonen2463 2 роки тому +1

    Mind blown... Able to do arithmetic on the meaning of words... I did not see that one coming :o A killer explanation on the subject thanks!! :D

  • @UserName________
    @UserName________ Рік тому +1

    How far we've come only 3 years later.

  • @nolisto1
    @nolisto1 Рік тому +3

    Watching in 2023 after discovering embedding in open ai api

  • @IvanBerdichevsky
    @IvanBerdichevsky 6 місяців тому +2

    Bro I feel like we're going to start using AI jargon as popular lingo very VERY soon. lol "Not in this dataset" , "Elaborate" , "You need to fine-tune yourself buddy"

  • @flomo1743
    @flomo1743 2 місяці тому +1

    Can someone explain the compression of information from that hidden layer. Is it basically training of the model that allows the hidden layer to adjust and define meaningful weights to each node, that leads to it not needing the same length vector as the input vector to produce a meaningful output? Or am I missing something here. Also is there a way to conceptualize these say 1000 dimensional vectors or is it just something you have to go with ?

  • @MenacingBanjo
    @MenacingBanjo 2 роки тому

    Came back here because I fell in love with the Semantle game that came out a couple of months ago.

  • @theshuman100
    @theshuman100 5 років тому +1

    word embeddings are the friends we make along the way

  • @DrD0000M
    @DrD0000M 5 років тому +36

    3rd result for dog is "bark incessantly."
    Even AI knows dogs are annoying mutants. Fun fact: Wolves don't bark, well, almost never.

    • @Dawn-hd5xx
      @Dawn-hd5xx 5 років тому +7

      Wild cats also don't meow. Even feral "domestic" (as in the species) cats don't meow, it's only towards humans that they do.

    • @NicknotNak
      @NicknotNak 4 роки тому +2

      Duddino Gatto they mew. But they outgrow it pretty quickly. Humans don’t babble like babies when we grow up, but if that was the only think our feline overlords responded to, we would.

  • @dialecticalmonist3405
    @dialecticalmonist3405 2 роки тому

    Santa giving you "ho ho ho" was both terrifying and humorous at the same time. Wow.

  • @oneMeVz
    @oneMeVz 4 роки тому

    i think this video just have me a better understanding of neural networks

  • @edoardoschnell
    @edoardoschnell 5 років тому

    This is über amazing. I wonder if you could use that to predict cache hits and misses

  • @redjr242
    @redjr242 5 років тому +2

    This is fascinating! Might we be able to represent language in the abstract as a vector space? Furthermore, similar but slightly different words in different languages are represented by similar by slightly different vectors in this vector space?

  • @siddharth__pandey
    @siddharth__pandey 5 років тому +1

    Came here from DeepLearning.ai specialization I was doing when I couldn't grab Word2vec.. Nice explanation

  • @Veptis
    @Veptis 5 років тому +2

    it's more than slightly surprising that you can explain this concept in 17 minutes, instead of going to a semester full of lectures.

    • @Rockyzach88
      @Rockyzach88 Рік тому +2

      Yeah but did you "learn" or just "understand while listening". Those are not the same things. Although, they may complement each other nicely in some cases.

  • @alisalloum629
    @alisalloum629 2 роки тому

    damn that's the best enjoyable informative video I've seen in a while

  • @RafaelCouto
    @RafaelCouto 5 років тому +2

    Plz more AI videos, they are awesome!

  • @HeavisideDelta
    @HeavisideDelta 7 місяців тому

    This is one of the coolest things i've seen in a while. Just thinking how small a neighbourhood of one word/vector should we take ? Or how does the implementation of context affect the choice of optimal neighbourhoods ?

    • @HeavisideDelta
      @HeavisideDelta 7 місяців тому

      And contexts themselves vary from a person to another depending on how they experienced life. So it would be interesting to see also a set of optimal contexts and that would affect the whole thing.

  • @helifalic
    @helifalic 5 років тому

    This blew my mind. Simply wonderful!

  • @Gargamelle
    @Gargamelle 3 роки тому +1

    If you train 2 networks with different languages I guess the latent space? would be similar. And the differences could be really relevant to how we thought differently due to using different language

  • @TrevorOFarrell
    @TrevorOFarrell 5 років тому

    Nice thinkpad rob! I'm using the same version of x1 carbon with the touch bar as my daily machine. Great taste.

  • @werthersoriginal
    @werthersoriginal 5 років тому

    *You are the company you keep*

  • @carlossegura403
    @carlossegura403 4 роки тому +1

    Wow, it is 2020, and I haven't used Gensim and GloVe in years - ever since the release of BERT and GPT.

  • @worldaviation4k
    @worldaviation4k 5 років тому +3

    is the diagram with angles and arrows going off in all directions just for us to visualise it rather than how computers are looking at it, I didn't think they'd be calculating degrees. I thought it would be more about numbers of how close the match is like 0-100

  • @vic2734
    @vic2734 5 років тому +1

    Beautiful concept. Thanks for sharing!

  • @robinw77
    @robinw77 5 років тому +3

    When the room started getting brighter and brighter, I thought the rapture was happening xD

  • @joshuakessler8346
    @joshuakessler8346 2 місяці тому

    Excellent video

  • @jellyboy00
    @jellyboy00 5 років тому +7

    I think this looks more like an auto-encoder than GAN

    • @cmilkau
      @cmilkau 5 років тому +5

      It's structurally the same as an AE, but it's trained differently. An AE has to reconstruct its input, but this network needs to find closely related, but different words.

  • @joedempseysr.3376
    @joedempseysr.3376 4 роки тому

    Amazing correlations for only 300 vectors. Next, you must assign a "meaning" to each vector to get better correlations and tags of context. One could also increase the number of vectors.

    • @harrycally2565
      @harrycally2565 4 роки тому +1

      Joe Dempsey, Sr. It’s not the number of vectors, rather the dimension of the vectors

  • @SpiderTalon
    @SpiderTalon 4 роки тому

    I would love to see a followup vid using verbs/adverbs rather than just nouns.

  • @SanderBuruma
    @SanderBuruma 5 років тому +1

    absolutely fascinating

  • @rishabhmahajan6607
    @rishabhmahajan6607 3 роки тому

    Brilliantly explained! Thank you for this video