example_LM.py

import numpy as np

# Create a very simple unigram LM with a small vocabulary
vocab = ['<s>', 'This', 'LM', 'is', 'stupid', 'cool', '</s>']
word2index = {w: i for i, w in enumerate(vocab)}
probabilities = np.array([[0.01, 0.94, 0.01, 0.01, 0.01, 0.01, 0.01],
                          [0.01, 0.01, 0.94, 0.01, 0.01, 0.01, 0.01],
                          [0.01, 0.01, 0.01, 0.94, 0.01, 0.01, 0.01],
                          [0.01, 0.01, 0.01, 0.01, 0.47, 0.48, 0.01],
                          [0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.94],
                          [0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.94],
                          [0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.94]])
stupid_lm = lambda s: probabilities[word2index.get(s.split()[-1], -1), :]