Calculate Word Similarity

s10.py

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)