Stratul de embedding

Rețele Neuronale Recurente (RNN) pentru Modelare a Limbajului cu Keras

David Cecchini

Data Scientist

De ce embeddings

Avantaje:

Reducerea dimensiunii

one_hot = np.array((N, 100000))
embedd = np.array((N, 300))

Reprezentare densă
- king - man + woman = queen
Transfer learning

Dezavantaje:

Mulți parametri de antrenat: antrenarea durează mai mult

Utilizare în keras

În keras:

from tensorflow.keras.layers import Embedding

model = Sequential()

# Use as the first layer
model.add(Embedding(input_dim=100000,

                    output_dim=300,

                    trainable=True,

                    embeddings_initializer=None,

                    input_length=120))

Transfer learning

Transfer learning pentru modele de limbaj

GloVE
word2vec
BERT

În keras:

from tensorflow.keras.initializers import Constant

model.add(Embedding(input_dim=vocabulary_size,
                    output_dim=embedding_dim,

                    embeddings_initializer=Constant(pre_trained_vectors))

Utilizarea vectorilor preantrenați GloVE

Site oficial: https://nlp.stanford.edu/projects/glove/

# Get hte GloVE vectors
def get_glove_vectors(filename="glove.6B.300d.txt"):
    # Get all word vectors from pre-trained model
    glove_vector_dict = {}
    with open(filename) as f:
        for line in f:

            values = line.split()

            word = values[0]
            coefs = values[1:]

            glove_vector_dict[word] = np.asarray(coefs, dtype='float32')


    return glove_vector_dict

Utilizarea GloVE pentru o sarcină specifică

# Filter GloVE vectors to specific task
def filter_glove(vocabulary_dict, glove_dict, wordvec_dim=300):

    # Create a matrix to store the vectors
    embedding_matrix = np.zeros((len(vocabulary_dict) + 1, wordvec_dim))

    for word, i in vocabulary_dict.items():
        embedding_vector = glove_dict.get(word)

        if embedding_vector is not None:
            # words not found in the glove_dict will be all-zeros.
            embedding_matrix[i] = embedding_vector


    return embedding_matrix

Să exersăm!

Rețele Neuronale Recurente (RNN) pentru Modelare a Limbajului cu Keras