FastText Embedding

Pros:

  1. Can handle any language due to the Sub-word Tokenizer (specially the languages where sentences are not separated by space)
  2. Can handle more rare words than GloVe Embedding or Word2Vec Embedding
  3. More morphological awareness as it captures the nuances of word morphology through subwords

Cons:

  1. Computationally inefficient for a large dataset due to multiple representation of same word

References


Related Notes