Word sequence embeddings

blog_lm1b_3.py

def forward(sentence):
    # Tokenize characters and words
    word_ids = [vocab.word_to_id(w) for w in sentence.split()]
    char_ids = [vocab.word_to_char_ids(w) for w in sentence.split()]

    if sentence.find('<S>') != 0:
        sentence = '<S> ' + sentence

    for i in xrange(len(word_ids)):
        inputs[0, 0] = word_ids[i]
        char_ids_inputs[0, 0, :] = char_ids[i]

        # Add 'lstm/lstm_0/control_dependency' if you want to dump previous layer
        # LSTM.
        lstm_emb = sess.run(t['lstm/lstm_1/control_dependency'],
                        feed_dict={t['char_inputs_in']: char_ids_inputs,
                                   t['inputs_in']: inputs,
                                   t['targets_in']: targets,
                                   t['target_weights_in']: weights})
    return lstm_emb

``