For our embedding scheme, we are going to be using the implementation of GloVe from the previous chapter:
from collections import Counter, defaultdictimport osfrom random import shuffleimport tensorflow as tfimport nltk
class GloVeModel(): def __init__(self, embedding_size, window_size, max_vocab_size=100000, min_occurrences=1, scaling_factor=3/4, cooccurrence_cap=100, batch_size=512, learning_rate=0.05): self.embedding_size = embedding_size#First we define the hyper-parameters of our model if isinstance(context_size, tuple): self.left_context, self.right_context = context_size elif isinstance(context_size, int): self.left_context = self.right_context = context_size self.max_vocab_size = max_vocab_size self.min_occurrences ...
