Théo Szymkowiak
Aug 22, 2017 · 1 min read

Hi Rudra,

The code is using pre-trained embeddings provided by the Keras library (they are built-in). If the text contains an unknown word (a word for which there is no embedding), the algorithm drops that word.

I hope I answered your questions!

)
    Théo Szymkowiak

    Written by

    @McGillU CS Grad. Founder, McGill AI Society (https://mcgillai.com). Full Stack Dev at Clay (https://base.run). Entrepreneur.