def main(_):
data_dir = cfg.DATA_DIR
vocab, rev_vocab = initialize_vocab(FLAGS.vocab)
# gpu setting
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
tf.reset_default_graph()
encoder = Encoder(size=2 * cfg.lstm_num_hidden)
decoder = Decoder(output_size=2 * cfg.lstm_num_hidden)
qa = QASystem(encoder, decoder, FLAGS.embed)
with tf.Session(config=config) as sess:
init = tf.global_variables_initializer()
sess.run(init)
load_train_dir = get_normalized_train_dir(FLAGS.ckpt)
initialize_model(sess, qa, load_train_dir)
print(
'*********************************************************************'
)
print(
"Welcome! You can use this to explore the behavior of the model.")
print(
'*********************************************************************'
)
while True:
print('-------------------')
print('Input the context: ')
print('-------------------')
sentence = raw_input()
print('-------------------')
print('Input the question: ')
print('-------------------')
query = raw_input()
raw_context = nltk.word_tokenize(sentence)
context = sentence_to_token_ids(sentence,
vocab,
tokenizer=nltk.word_tokenize)
question = sentence_to_token_ids(query,
vocab,
tokenizer=nltk.word_tokenize)
context_in = mask_input(context, cfg.context_max_len)
question_in = mask_input(question, cfg.question_max_len)
start, end = qa.answer(sess, [context_in], [question_in])
answer = ' '.join(raw_context[start[0]:end[0] + 1])
print('==========================================')
print('ANSWER: {}'.format(answer))
print('==========================================')
def run_func():
config = Config()
train = squad_dataset(config.question_train, config.context_train,
config.answer_train)
dev = squad_dataset(config.question_dev, config.context_dev,
config.answer_dev)
# print(config.question_train)
embed_path = config.embed_path
vocab_path = config.vocab_path
# print(config.embed_path, config.vocab_path)
vocab, rev_vocab = initialize_vocab(vocab_path)
embeddings = get_trimmed_glove_vectors(embed_path)
encoder = Encoder(config.hidden_size)
decoder = Decoder(config.hidden_size)
qa = QASystem(encoder, decoder, embeddings, config)
with tf.Session() as sess:
# ====== Load a pretrained model if it exists or create a new one if no pretrained available ======
qa.initialize_model(sess, config.train_dir)
# train process
# qa.train(sess, [train, dev], config.train_dir)
# em = qa.evaluate_model(sess, dev)
# run process
while True:
question = input('please input question: ')
if question == 'exit':
break
raw_context = input('please input context: ')
if raw_context == 'exit':
break
question = [
vocab[x] if x in vocab.keys() else 2 for x in question.split()
]
context = [
vocab[x] if x in vocab.keys() else 2
for x in raw_context.split()
]
test = [[question], [context], [[1, 2]]]
a_s, a_e = qa.answer(sess, test)
if a_e == a_s:
print("answer: ", raw_context.split()[a_s[0]])
else:
print("answer: ",
' '.join(raw_context.split()[a_s[0]:a_e[0] + 1]))
def main(_):
data_dir = cfg.DATA_DIR
vocab, rev_vocab = initialize_vocab(FLAGS.vocab)
# gpu setting
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
tf.reset_default_graph()
encoder = Encoder(size=2 * cfg.lstm_num_hidden)
decoder = Decoder(output_size=2 * cfg.lstm_num_hidden)
qa = QASystem(encoder, decoder, FLAGS.embed)
with tf.Session(config=config) as sess:
init = tf.global_variables_initializer()
sess.run(init)
load_train_dir = get_normalized_train_dir(FLAGS.ckpt)
initialize_model(sess, qa, load_train_dir)
print('*********************************************************************')
print("Welcome! You can use this to explore the behavior of the model.")
print('*********************************************************************')
while True:
print('-------------------')
print('Input the context: ')
print('-------------------')
sentence = raw_input()
print('-------------------')
print('Input the question: ')
print('-------------------')
query = raw_input()
raw_context = nltk.word_tokenize(sentence)
context = sentence_to_token_ids(sentence, vocab, tokenizer=nltk.word_tokenize)
question = sentence_to_token_ids(query, vocab, tokenizer=nltk.word_tokenize)
context_in = mask_input(context, cfg.context_max_len)
question_in = mask_input(question, cfg.question_max_len)
start, end = qa.answer(sess, [context_in], [question_in])
answer = ' '.join(raw_context[start[0]: end[0] + 1])
print('==========================================')
print('ANSWER: {}'.format(answer))
print('==========================================')
