大家好，我为聊天机器人开发了两个 RNN 模型。假设用户说：“告诉我明天巴黎的天气如何”。第一个模型将能够识别用户的意图 WEATHER_INFO ，而第二个模型将能够从 LOC:Paris 和 DATE:tomorrow 等短语中提取有意义的信息当然还有许多其他意图类别，例如 MUSIC_PLAY 等等. 由于这两个模型没有以任何方式链接到同一个短语，我们可以得到例如结果意图：WEATHER_INFO 和 TITLE:Paris，其中插槽 TITLE 与 MUSIC_PLAY 意图相关联 许多研究人员试图通过创建联合模型来提高性能两个模型使用另一个模型以避免这种错误在这里我的插槽填充代码
from keras.models import Model, Input
from keras.layers import LSTM, Embedding, Dense, TimeDistributed, Dropout, Bidirectional
import keras as k
from keras_contrib.layers import CRF
# input = Input(shape=(140,))
# input = Input(shape=(len(X_train),max_len))
input = Input(shape=(max_len,))
# word_embedding_size = 150
word_embedding_size = 150
n_words = len(token_ids)
# Embedding Layer
model = Embedding(input_dim=n_words, output_dim=word_embedding_size, input_length=max_len)(input)
# model = Embedding(input_dim=n_words, output_dim=word_embedding_size, input_length=140)(input)
# BI-LSTM Layer
model = Bidirectional(LSTM(units=word_embedding_size,
return_sequences=True,
dropout=0.5,
recurrent_dropout=0.5,
kernel_initializer=k.initializers.he_normal()))(model)
model = LSTM(units=word_embedding_size * 2,
return_sequences=True,
dropout=0.5,
recurrent_dropout=0.5,
kernel_initializer=k.initializers.he_normal())(model)
# TimeDistributed Layer
model = TimeDistributed(Dense(n_tags, activation="relu"))(model)
# CRF Layer
crf = CRF(n_tags)
out = crf(model) # output
model = Model(input, out)
# In[]
# model compile and fit
from keras.callbacks import ModelCheckpoint
import matplotlib.pyplot as plt
# Optimiser
adam = k.optimizers.Adam(lr=0.0005, beta_1=0.9, beta_2=0.999)
# Compile model
model.compile(optimizer=adam, loss=crf.loss_function, metrics=[crf.accuracy, 'accuracy'])
model.summary()
# Saving the best model only
filepath = "ner-bi-lstm-td-model-{val_accuracy:.2f}.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='val_accuracy', verbose=1, save_best_only=True, mode='max')
callbacks_list = [checkpoint]
# Fit the best model
history = model.fit(X_train, y_train, batch_size=256, epochs=10, validation_split=0.1, verbose=1,
callbacks=callbacks_list)
这里是意图检测NN的代码
#CNN architecture
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
from keras import layers
batch_size = 128
epochs = 12
if nn_architecture == 'CNN':
model_CNN = Sequential()
e = Embedding(vocab_size, 300, weights=[embedding_matrix], input_length=max_length, trainable=False)
model_CNN.add(e)
model_CNN.add(Dropout(0.2))
# we add a Convolution1D, which will learn filters
# word group filters of size filter_length:
filters = 50
kernel_size = 3
hidden_dims = 250
model_CNN.add(layers.Conv1D(filters,
kernel_size,
padding='valid',
activation='relu',
strides=1))
# we use max pooling:
model_CNN.add(layers.GlobalMaxPooling1D())
# We add a vanilla hidden layer:
model_CNN.add(Dense(hidden_dims))
model_CNN.add(Dropout(0.2))
model_CNN.add(layers.Activation('relu'))
# We project onto a single unit output layer, and squash it with a sigmoid:
model_CNN.add(Dense(nbClasses)) # no_of_categories
model_CNN.add(layers.Activation('sigmoid'))
model_CNN.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
history_CNN =model_CNN.fit(X_train, Y_train_c,
batch_size=batch_size,
epochs=epochs,
#validation_split=0.2
)
# Epoch 12/12
# 38771/38771 [==============================] - 11s 276us/step -
#loss: 0.0046 - accuracy: 0.9985
我想要的是合并这两种架构以获得这个
请帮助我...提前谢谢