Verhindern, über-Einbau von text-Klassifikation mit Word einbetten mit LSTM

Ziel :

• Identifizierung Klasse label mit Benutzer eingegebene Frage (wie Frage
  Antwort system).
• Daten extrahiert, die von Großen PDF-Datei, und brauchen, um vorherzusagen,
  Seitenzahl basierend auf Benutzereingaben.
• Hauptsächlich verwendet in der policy-Dokument, wo
  Benutzer haben Fragen über Politik und zeigen müssen bestimmte Seite
  Anzahl.

---

Bisherige Umsetzung :
Applied elastic-search, aber sehr geringer Genauigkeit, da die Benutzer geben Sie einen text ein wie "ich muss" == "wollen"

---

Dataset-Informationen :
Dataset enthält jede Zeile als Text( oder Absatz) und Label (Seitenzahlen). hier dataset klein ist, habe ich nur 500 Zeilen.

Aktuelle Implementierung :

• Angewendet word-einbetten(Handschuh) mit LSTM in Keras-und back-end ist
  Tensor-flow
• Angewendet Droupout
• Angewendet ActivityRegularization
• Angewendet L2 W_regularizer( von 0,1 bis 0,001)
• Auf verschiedene nb_epoch von 10-600
• Geändert EMBEDDING_DIM von 100-300-Handschuh-Daten

---

Angewandte NLP für,

• In Kleinschreibung konvertieren
• Entfernen Stop Wort Englisch
• Wortstamm
• Entfernen Nummern
• Entfernen, die URL und die IP-Adresse

Ergebnis : die Genauigkeit der Testdaten(oder Validierung von Daten) ist mit 23% aber auf Zug Daten 91%

---

Code :

import time
from time import strftime

import numpy as np
from keras.callbacks import CSVLogger, ModelCheckpoint
from keras.layers import Dense, Input, LSTM, ActivityRegularization
from keras.layers import Embedding, Dropout,Bidirectional
from keras.models import Model
from keras.preprocessing.sequence import pad_sequences
from keras.preprocessing.text import Tokenizer
from keras.regularizers import l2
from keras.utils import to_categorical

import pickle
from DataGenerator import *

BASE_DIR = ''
GLOVE_DIR = 'D:/Dataset/glove.6B'  # BASE_DIR + '/glove.6B/'

MAX_SEQUENCE_LENGTH = 50
MAX_NB_WORDS = 20000
EMBEDDING_DIM = 300
VALIDATION_SPLIT = 0.2

# first, build index mapping words in the embeddings set
# to their embedding vector
np.random.seed(1337)  # for reproducibility

print('Indexing word vectors.')

t_start = time.time()

embeddings_index = {}

if os.path.exists('pickle/glove.pickle'):
    print('Pickle found..')
    with open('pickle/glove.pickle', 'rb') as handle:
        embeddings_index = pickle.load(handle)
else:
    print('Pickle not found...')
    f = open(os.path.join(GLOVE_DIR, 'glove.6B.300d.txt'), encoding='utf8')
    for line in f:
        values = line.split()
        word = values[0]
        coefs = np.asarray(values[1:], dtype='float32')
        embeddings_index[word] = coefs
    f.close()
    with open('pickle/glove.pickle', 'wb') as handle:
        pickle.dump(embeddings_index, handle, protocol=pickle.HIGHEST_PROTOCOL)

print('Found %s word vectors.' % len(embeddings_index))

# second, prepare text samples and their labels
print('Processing text dataset')

texts = []  # list of text samples
labels = []  # list of label ids
labels_index = {}  # dictionary mapping label name to numeric id

(texts, labels, labels_index) = get_data('D:/PolicyDocument/')

print('Found %s texts.' % len(texts))

# finally, vectorize the text samples into a 2D integer tensor
tokenizer = Tokenizer(nb_words=MAX_NB_WORDS)
tokenizer.fit_on_texts(texts)
sequences = tokenizer.texts_to_sequences(texts)

word_index = tokenizer.word_index
print('Found %s unique tokens.' % len(word_index))
data = pad_sequences(sequences, maxlen=MAX_SEQUENCE_LENGTH)

labels = to_categorical(np.asarray(labels))
print('Shape of data tensor:', data.shape)
print('Shape of label tensor:', labels.shape)

# split the data into a training set and a validation set
indices = np.arange(data.shape[0])
np.random.shuffle(indices)
data = data[indices]
labels = labels[indices]
num_validation_samples = int(VALIDATION_SPLIT * data.shape[0])

x_train = data[:-num_validation_samples]
y_train = labels[:-num_validation_samples]
x_val = data[-num_validation_samples:]
y_val = labels[-num_validation_samples:]

# prepare embedding matrix
num_words = min(MAX_NB_WORDS, len(word_index))
embedding_matrix = np.zeros((num_words + 1, EMBEDDING_DIM))
print('Preparing embedding matrix. :', embedding_matrix.shape)
for word, i in word_index.items():
    embedding_vector = embeddings_index.get(word)
    if embedding_vector is not None:
        # words not found in embedding index will be all-zeros.
        embedding_matrix[i] = embedding_vector

# load pre-trained word embeddings into an Embedding layer
# note that we set trainable = False so as to keep the embeddings fixed
embedding_layer = Embedding(embedding_matrix.shape[0],
                            embedding_matrix.shape[1],
                            weights=[embedding_matrix],
                            input_length=MAX_SEQUENCE_LENGTH,
                            mask_zero=True,
                            trainable=False)

print('Training model.')

csv_file = "logs/training_log_" + strftime("%Y-%m-%d %H-%M", time.localtime()) + ".csv"
model_file = "models/Model_" + strftime("%Y-%m-%d %H-%M", time.localtime()) + ".mdl"
print("Model file:" + model_file)
csv_logger = CSVLogger(csv_file)

# train a 1D convnet with global maxpooling
sequence_input = Input(shape=(MAX_SEQUENCE_LENGTH,), dtype='int32')
embedded_sequences = embedding_layer(sequence_input)

rate_drop_lstm = 0.15 + np.random.rand() * 0.25
num_lstm = np.random.randint(175, 275)
rate_drop_dense = 0.15 + np.random.rand() * 0.25

x = LSTM(num_lstm, return_sequences=True, W_regularizer=l2(0.001))(embedded_sequences)
x = Dropout(0.5)(x)
x = LSTM(64)(x)
x = Dropout(0.25)(x)
x = ActivityRegularization(l1=0.01, l2=0.001)(x)
preds = Dense(len(labels_index), activation='softmax')(x)

model = Model(sequence_input, preds)
model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['acc'])

model_checkpoint = ModelCheckpoint(model_file, monitor='val_loss', verbose=0, save_best_only=True,
                                   save_weights_only=False, mode='auto')

model.fit(x_train, y_train,
          batch_size=1,
          nb_epoch=600,
          validation_data=(x_val, y_val), callbacks=[csv_logger, model_checkpoint])

score = model.evaluate(x_val, y_val, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])

t_end = time.time()
total = t_end - t_start
ret_str = "Time needed(s): " + str(total)
print(ret_str)