Deep Learning Research Review: Natural Language Processing
Since deep learning loves math, we’re going to represent each word as a d-dimensional vector.Extracting the rows from this matrix can give us a simple initialization of our word vectors.The above cost function is basically saying that we’re going to add the log probabilities of ‘I’ and ‘love’ as well as ‘NLP’ and ‘love’ (where ‘love’ is the center…
Read More...