def TrainLstmCrf(data_name, model_name):
n_classes = 4
max_len = 75
batch_size = 128
epoch = 100
tags = ['S', 'B', 'I', 'E']
sentences, words = get_sents(datasets=data_name)
print(len(sentences), len(words))
word2idx = {w: i + 1 for i, w in enumerate(words)}
tag2idx = {t: i for i, t in enumerate(tags)}
vocab_size = len(words)
X = [[word2idx[w[0]] for w in s] for s in sentences]
X = pad_sequences(maxlen=max_len,
sequences=X,
padding="post",
value=vocab_size - 1)
y = [[tag2idx[w[1]] for w in s] for s in sentences]
y = pad_sequences(maxlen=max_len,
sequences=y,
padding="post",
value=tag2idx["E"])
y = [to_categorical(i, num_classes=n_classes) for i in y]
# 获得数据
X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size=0.1)
print(len(X_tr), len(y_tr), len(X_te), len(y_te))
s = np.asarray([max_len] * batch_size, dtype='int32')
# 建立模型
word_ids = Input(batch_shape=(batch_size, max_len), dtype='int32')
sequence_lengths = Input(batch_shape=[batch_size, 1], dtype='int32')
print(sequence_lengths)
word_embeddings = Embedding(vocab_size, n_classes)(word_ids)
blstm = Bidirectional(LSTM(units=50,
return_sequences=True))(word_embeddings)
model = TimeDistributed(Dense(4, activation='tanh'))(blstm)
crf = CrfModel()
pred = crf(inputs=[model, sequence_lengths])
model = Model(inputs=[word_ids, sequence_lengths], outputs=[pred])
print("word_ids:{}".format(word_ids))
print("sequence_lengths:{}".format(sequence_lengths))
model.compile(optimizer="rmsprop", loss=crf.loss, metrics=['accuracy'])
print(model.summary())
k = 0
for batch_x, batch_y in minibatches(X_tr, y_tr, batch_size=batch_size):
model.fit([batch_x, s],
np.array(batch_y),
epochs=epoch,
batch_size=batch_size)
k += 1
if k % 50 == 0:
model.save("./models/{}_{}".format(k, model_name))
print("saved")
# 保存模型
model.save(model_name)
pos_emb = Embedding(input_dim=len(pos),
output_dim=10,
input_length=max_len)(pos_input)
modified_input = keras.layers.concatenate([word_emb, pos_emb])
model_1 = Bidirectional(
LSTM(units=50, return_sequences=True,
recurrent_dropout=0.1))(modified_input)
model = TimeDistributed(Dense(50, activation="relu"))(
model_1) # a dense layer as suggested by neuralNer
crf = CRF(n_tags) # CRF layer
out = crf(model) # output
model = Model([input, pos_input], out)
model.compile(optimizer="rmsprop",
loss=crf.loss_function,
metrics=[crf.accuracy])
print(model.summary())
history = model.fit([X_tr, X_pos_tr],
np.array(y_tr),
batch_size=32,
epochs=60,
validation_split=0.1,
verbose=1)
#Testing
test_pred = model.predict([X_te, X_pos_te], verbose=1)
idx2tag = {i: w for w, i in tag2idx.items()}
pred_labels = pred2label(test_pred)
test_labels = pred2label(y_te)
print("Recall, Precision and F-score are",
get_recall_precision(test_labels, pred_labels, "Destination"))
model.save("BILSTM+CRF_with_pos_without_embeddings.model")
