Last active
March 19, 2019 22:58
-
-
Save VXU1230/c0a68009fed196fcdb7c3e0e919d7e2e to your computer and use it in GitHub Desktop.
Calculate Word Similarity
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
NUM_SIM = 5 | |
def get_similarity(sim_examples, embed_weights): | |
norm = tf.sqrt(tf.reduce_sum(tf.square(embed_weights), 1, keepdims=True)) | |
norm_embed_matrix = embed_weights / norm | |
valid_embed = tf.nn.embedding_lookup(norm_embed_matrix, sim_examples) | |
sim_matrix = tf.matmul(valid_embed, tf.transpose(norm_embed_matrix)) | |
return sim_matrix | |
def print_eval(valid_examples, sim_matrix, reverse_dic): | |
top_k = 3 | |
for i in range(NUM_SIM): | |
valid_word = reverse_dic[valid_examples[i]] | |
nearest = np.argsort(-sim_matrix[i, :])[1:top_k + 1] | |
log = '\nNearest to %s:' % valid_word | |
for k in range(top_k): | |
close_word = reverse_dic[nearest[k]] | |
log = '%s %s,' % (log, close_word) | |
print(log) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment