NLP Demystified 12: Capturing Word Meaning with Embeddings

Поділитися
Вставка
  • Опубліковано 8 січ 2025

КОМЕНТАРІ • 19

  • @futuremojo
    @futuremojo  2 роки тому +2

    CORRECTION: at 1:33, that should be "20,000-element vector" .
    Timestamps
    00:00:00 Word Vectors
    00:00:37 One-Hot Encoding and its shortcomings
    00:02:07 What embeddings are and why they're useful
    00:05:12 Similar words share similar contexts
    00:06:15 Word2Vec, a way to automatically create word embeddings
    00:08:08 Skip-Gram With Negative Sampling (SGNS)
    00:17:11 Three ways to use word vectors in models
    00:18:48 DEMO: Training and using word vectors
    00:41:29 The weaknesses of static word embeddings

  • @moistnar
    @moistnar Рік тому +10

    So I attend a really, REALLY prestigious university in the US and I took a course on Neural Networks this last term--this video series has higher lecture quality than that. You are very good at teaching these concepts

    • @futuremojo
      @futuremojo  Рік тому +2

      Thank you!

    • @caiyu538
      @caiyu538 Рік тому +1

      A lot of UA-camrs teach better than a lot of “professors”.

  • @michaelm358
    @michaelm358 Рік тому +3

    I have watched 5 videos on this subject in the last 2 days, and browsed dozens. This one is OUTSTANDING!!! By far the best i have seen. Wow!
    I will do the whole NLP course. Very grateful for Huge effort it took

    • @futuremojo
      @futuremojo  Рік тому

      Thank you! I hope you get a lot out of it.

  • @fayezalhussein7115
    @fayezalhussein7115 2 місяці тому

    You are very good at teaching

  • @AshishMishra-rk4df
    @AshishMishra-rk4df 10 місяців тому +1

    Great work 👍

  • @lochanaemandi6405
    @lochanaemandi6405 Рік тому

    In SGNS, when you are talking about matrices of context and target embeddings (10000 * 300), what do these matrices have/contain before the training has started (collection of one hot encodings or arbitrary numbers)? At 17:00, I also did not understand how only taking the target word embeddings would be sufficient to capture similarity between words.

  • @caiyu538
    @caiyu538 Рік тому +1

    I saw openai also provide embedding tool. It seems that this make easier than the old library such as NLTK,spacy, making them outdated? It make these concepts as a black box for us. We do not need to know in detail if only to use it.

    • @futuremojo
      @futuremojo  Рік тому +1

      Absolutely. LLM APIs (even open source ones), hide all the details and make it easy for anyone to build NLP applications. We explore these APIs in part two and see how things like sentiment analysis can be done with a single line now.

    • @caiyu538
      @caiyu538 Рік тому

      @@futuremojo Great, your lectures uncovered these concepts hidden in the Blackbox.

    • @caiyu538
      @caiyu538 Рік тому

      @@futuremojo I also look forward to these lectures. Thank your lectures to know so many hidden concepts.

  • @dmytrokulaiev9083
    @dmytrokulaiev9083 Рік тому +2

    Are you planning to do courses on other machine learning topics, such as computer vision?

    • @futuremojo
      @futuremojo  Рік тому +6

      I probably won't build another course. This one took a year. I would consider more frequent, short-form videos though. What would you find useful?

    • @dmytrokulaiev9083
      @dmytrokulaiev9083 Рік тому +2

      @@futuremojo Perhaps some material on diffusion models

    • @hungreee
      @hungreee Рік тому

      @@futuremojo yes definitely

  • @kevinoudelet
    @kevinoudelet 11 місяців тому

    Thank you !

  • @loicbaconnier9150
    @loicbaconnier9150 2 роки тому

    Awesome !