Generates a word rank-based probabilistic sampling table.
make_sampling_table(size, sampling_factor = 1e-05)
Int, number of possible words to sample.
The sampling factor in the word2vec formula.
An array of length
size where the ith entry is the
probability that a word of rank i should be sampled.
Used for generating the
sampling_table argument for
sampling_table[[i]] is the probability of sampling the word i-th most common
word in a dataset (more common words should be sampled less frequently, for balance).
The sampling probabilities are generated according to the sampling distribution used in word2vec:
p(word) = min(1, sqrt(word_frequency / sampling_factor) / (word_frequency / sampling_factor))
We assume that the word frequencies follow Zipf's law (s=1) to derive a numerical approximation of frequency(rank):
frequency(rank) ~ 1/(rank * (log(rank) + gamma) + 1/2 - 1/(12*rank))
gamma is the Euler-Mascheroni constant.
The word2vec formula is: p(word) = min(1, sqrt(word.frequency/sampling_factor) / (word.frequency/sampling_factor))