# Word2Vec The skip-gram model is simply taking a word and predicting the surrounding words from that word.  ### Continuous Bag of Words (CBOW) A question I had was why is it called continuous bag of words. The answer is touched on here: [natural language - Why CBOW model is called "continuous"? - Cross Validated](https://stats.stackexchange.com/questions/444270/why-cbow-model-is-called-continuous#:~:text=%22We%20denote%20this%20model%20further,representations%20previously%20used%20in%20NLP.) Basically, we can reason about this as follows: > "We denote this model further as CBOW, as unlike standard bag-of-words model, it uses continuous distributed representation of the context". > Since word vectors are elements in $\mathbb{R}^n$, they are inherently continuous, as opposed to the discrete one-hot representations previously used in NLP. ### Distributed Bag of Words (DBOW) --- Date: 20210518 Links to: [Projection-vs-Embedding](/posts//posts//posts/Projection-vs-Embedding.md) References: * [Word2Vec: Distributed Representations of Words and Phrases and their Compositionality](https://www.youtube.com/watch?v=yexR53My2O4) * [Word2Vec tutorial](https://medium.com/@zafaralibagh6/a-simple-word2vec-tutorial-61e64e38a6a1) * [My blog post](https://www.nathanieldake.com/Deep_Learning/03-Recurrent_Neural_Networks-02-Word-Embeddings-and-Poetry.html) * [Learn word embedding](https://lilianweng.github.io/lil-log/2017/10/15/learning-word-embedding.html) * [Word to vec, whiteboard](https://photos.google.com/photo/AF1QipOxnUmAuyA5ZhGLV2aF3bVtxjoY_0ia3dnwhLyH) * [Word2Vec : Natural Language Processing - YouTube](https://www.youtube.com/watch?v=f7o8aDNxf7k) * [TFIDF : Data Science Concepts - YouTube](https://www.youtube.com/watch?v=OymqCnh-APA) * [A simple Word2vec tutorial. In this tutorial we are going to… | by Zafar Ali | Medium](https://medium.com/@zafaralibagh6/a-simple-word2vec-tutorial-61e64e38a6a1) * Notability, word2vec