I'm reading about Embedding layers, especially applied to NLP and word2vec, and they seem nothing more than an application of Autoencoders for dimensionality reduction. Are they different? If so, what are the differences between them?


Actually they are 3 different things (embedding layer, word2vec, autoencoder), though they can be used to solve similar problems. (i.e. dense representation of data)

Autoencoder is a type of neural network where the inputs and outputs are the same but in the hidden layer the dimensionality is reduced in order to get a more dense representation of the data.

Word2vec contains only 1 hidden layer but the inputs are the neighborhood words and the output is the word itself (or the other way around). So it cannot be an autoencoder cause the inputs and outputs are different.

Embedding layer is only a "simple" layer in a neural network. You can imagine it as a dictionary where a category (i.e word) is represented as a vector (list of numbers). The value of the vectors are defined by backpropagating the errors of the network.

  • $\begingroup$ I think word2vec has two "modes of operation" 1) input neighboring words and predict a word (like you described) or 2) input a word and predict next word. The second mode makes sense (go from one-hot to another one-hot, then cut the model open for the embedding). How does the first one work? $\endgroup$ Jun 11 at 13:38

Embedding layer, is used in auto-encoders to construct word2vec.

Embedding layer, are a type of layer, used in Deep Learning. You can find others here. Auto-encoders, are a type of architecture, where embedding layers are used. Using these architectures, one can calculate word2vec. word2vec values are calculated when words are fed into the auto-encoders.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.