Universal Sentence Encoder

Universal_sentence_encoder.py

module_url = "https://tfhub.dev/google/universal-sentence-encoder/1?tf-hub-format=compressed"

# Import the Universal Sentence Encoder's TF Hub module
embed = hub.Module(module_url)

# sample text
messages = [
# Smartphones
"My phone is not good.",
"Your cellphone looks great.",

# Weather
"Will it snow tomorrow?",
"Recently a lot of hurricanes have hit the US",

# Food and health
"An apple a day, keeps the doctors away",
"Eating strawberries is healthy",
]

similarity_input_placeholder = tf.placeholder(tf.string, shape=(None))
similarity_message_encodings = embed(similarity_input_placeholder)
with tf.Session() as session:
    session.run(tf.global_variables_initializer())
    session.run(tf.tables_initializer())
    message_embeddings_ = session.run(similarity_message_encodings, feed_dict={similarity_input_placeholder: messages})

    corr = np.inner(message_embeddings_, message_embeddings_)
    print(corr)
    heatmap(messages, messages, corr)
    
def heatmap(x_labels, y_labels, values):
    fig, ax = plt.subplots()
    im = ax.imshow(values)

    # We want to show all ticks...
    ax.set_xticks(np.arange(len(x_labels)))
    ax.set_yticks(np.arange(len(y_labels)))
    # ... and label them with the respective list entries
    ax.set_xticklabels(x_labels)
    ax.set_yticklabels(y_labels)

    # Rotate the tick labels and set their alignment.
    plt.setp(ax.get_xticklabels(), rotation=45, ha="right", fontsize=10,
         rotation_mode="anchor")

    # Loop over data dimensions and create text annotations.
    for i in range(len(y_labels)):
        for j in range(len(x_labels)):
            text = ax.text(j, i, "%.2f"%values[i, j],
                           ha="center", va="center", color="w", 
fontsize=6)

    fig.tight_layout()
    plt.show()