#23. Emojify

* Baseline model: Emojifier-V1

(1) Dataset EMOJISET

- X: 127 sentences / Y: a integer between 0~4 corresponding to an emoji for each sentence

(2) Overview of the Emojifier-V1

(3) Implementing Emojifier-V1

# GRADED FUNCTION: sentence_to_avg

def sentence_to_avg(sentence, word_to_vec_map):
    """
    Converts a sentence (string) into a list of words (strings). Extracts the GloVe representation of each word
    and averages its value into a single vector encoding the meaning of the sentence.
    
    Arguments:
    sentence -- string, one training example from X
    word_to_vec_map -- dictionary mapping every word in a vocabulary into its 50-dimensional vector representation
    
    Returns:
    avg -- average vector encoding information about the sentence, numpy-array of shape (50,)
    """
    
    # Step 1: Split sentence into list of lower case words (≈ 1 line)
    words = sentence.lower().split()

    # Initialize the average word vector, should have the same shape as your word vectors.
    avg = np.zeros((50, ))
    
    # Step 2: average the word vectors. You can loop over the words in the list "words".
    for w in words:
        avg += word_to_vec_map[w]
    avg = avg / len(words)
    
    
    return avg

 

- sentence_to_avg() 함수를 통해 얻은 값들을 forward propagation에 전달해 cost를 계산하고 backpropagate 시켜 softmax의 parameter를 업데이트 시킨다.

- 식은 다음과 같다:

 

# GRADED FUNCTION: model

def model(X, Y, word_to_vec_map, learning_rate = 0.01, num_iterations = 400):
    """
    Model to train word vector representations in numpy.
    
    Arguments:
    X -- input data, numpy array of sentences as strings, of shape (m, 1)
    Y -- labels, numpy array of integers between 0 and 7, numpy-array of shape (m, 1)
    word_to_vec_map -- dictionary mapping every word in a vocabulary into its 50-dimensional vector representation
    learning_rate -- learning_rate for the stochastic gradient descent algorithm
    num_iterations -- number of iterations
    
    Returns:
    pred -- vector of predictions, numpy-array of shape (m, 1)
    W -- weight matrix of the softmax layer, of shape (n_y, n_h)
    b -- bias of the softmax layer, of shape (n_y,)
    """
    
    np.random.seed(1)

    # Define number of training examples
    m = Y.shape[0]                          # number of training examples
    n_y = 5                                 # number of classes  
    n_h = 50                                # dimensions of the GloVe vectors 
    
    # Initialize parameters using Xavier initialization
    W = np.random.randn(n_y, n_h) / np.sqrt(n_h)
    b = np.zeros((n_y,))
    
    # Convert Y to Y_onehot with n_y classes
    Y_oh = convert_to_one_hot(Y, C = n_y) 
    
    # Optimization loop
    for t in range(num_iterations):                       # Loop over the number of iterations
        for i in range(m):                                # Loop over the training examples
            
            ### START CODE HERE ### (≈ 4 lines of code)
            # Average the word vectors of the words from the i'th training example
            avg = sentence_to_avg(X[i], word_to_vec_map)

            # Forward propagate the avg through the softmax layer
            z = np.dot(W, avg) + b
            a = softmax(z)

            # Compute cost using the i'th training label's one hot representation and "A" (the output of the softmax)
            cost = -np.sum(np.multiply(Y_oh[i], np.log(a)))
            ### END CODE HERE ###
            
            # Compute gradients 
            dz = a - Y_oh[i]
            dW = np.dot(dz.reshape(n_y,1), avg.reshape(1, n_h))
            db = dz

            # Update parameters with Stochastic Gradient Descent
            W = W - learning_rate * dW
            b = b - learning_rate * db
        
        if t % 100 == 0:
            print("Epoch: " + str(t) + " --- cost = " + str(cost))
            pred = predict(X, Y, W, b, word_to_vec_map)

    return pred, W, b

 

 

(4) Examining test set performance

- Training set: Accuracy: 0.977272727273 Test set: Accuracy: 0.857142857143

 

 

* Emojifier-V2: Using LSTMs in Keras

(1) Overview of the model

 

(2) Keras and mini-batching

- 많은 딥러닝 프레임워크에서 동일한 mini-batch에 있는 모든 sequence들은 같은 길이를 가져야 한다. 그래서 padding을 사용한다.

    - 최대 sequence 길이를 지정하고, 그 길이에 맞추어 모든 문장에 padding을 넣어준다.

    - "I love you" => (e_i, e_love, e_you, 0, 0, ..., 0)

 

(3) The Embedding layer

- 케라스에서 embedding matrix는 layer로 표현되며, 양의 정수(indices corresponding to words)를 embedding vector에 mapping시킨다.

# GRADED FUNCTION: sentences_to_indices

def sentences_to_indices(X, word_to_index, max_len):
    """
    Converts an array of sentences (strings) into an array of indices corresponding to words in the sentences.
    The output shape should be such that it can be given to `Embedding()` (described in Figure 4). 
    
    Arguments:
    X -- array of sentences (strings), of shape (m, 1)
    word_to_index -- a dictionary containing the each word mapped to its index
    max_len -- maximum number of words in a sentence. You can assume every sentence in X is no longer than this. 
    
    Returns:
    X_indices -- array of indices corresponding to words in the sentences from X, of shape (m, max_len)
    """
    
    m = X.shape[0]                                   # number of training examples
    
    # Initialize X_indices as a numpy matrix of zeros and the correct shape (≈ 1 line)
    X_indices = np.zeros((m, max_len))
    
    for i in range(m):                               # loop over training examples
        
        # Convert the ith training sentence in lower case and split is into words. You should get a list of words.
        sentence_words = [x.lower() for x in X[i].split()]
        
        # Initialize j to 0
        j = 0
        
        # Loop over the words of sentence_words
        for w in sentence_words:
            # Set the (i,j)th entry of X_indices to the index of the correct word.
            X_indices[i, j] = word_to_index[w]
            # Increment j to j + 1
            j = j + 1
            
    
    return X_indices

# GRADED FUNCTION: pretrained_embedding_layer

def pretrained_embedding_layer(word_to_vec_map, word_to_index):
    """
    Creates a Keras Embedding() layer and loads in pre-trained GloVe 50-dimensional vectors.
    
    Arguments:
    word_to_vec_map -- dictionary mapping words to their GloVe vector representation.
    word_to_index -- dictionary mapping from words to their indices in the vocabulary (400,001 words)

    Returns:
    embedding_layer -- pretrained layer Keras instance
    """
    
    vocab_len = len(word_to_index) + 1                  # adding 1 to fit Keras embedding (requirement)
    emb_dim = word_to_vec_map["cucumber"].shape[0]      # define dimensionality of your GloVe word vectors (= 50)
    
    ### START CODE HERE ###
    # Initialize the embedding matrix as a numpy array of zeros of shape (vocab_len, dimensions of word vectors = emb_dim)
    emb_matrix = np.zeros((vocab_len, emb_dim))
    
    # Set each row "index" of the embedding matrix to be the word vector representation of the "index"th word of the vocabulary
    for word, index in word_to_index.items():
        emb_matrix[index, :] = word_to_vec_map[word]

    # Define Keras embedding layer with the correct output/input sizes, make it non-trainable. Use Embedding(...). Make sure to set trainable=False. 
    embedding_layer = Embedding(vocab_len, emb_dim, trainable = False)
    ### END CODE HERE ###

    # Build the embedding layer, it is required before setting the weights of the embedding layer. Do not modify the "None".
    embedding_layer.build((None,))
    
    # Set the weights of the embedding layer to the embedding matrix. Your layer is now pretrained.
    embedding_layer.set_weights([emb_matrix])
    
    return embedding_layer

 

(3) Building the Emojifier-V2

# GRADED FUNCTION: Emojify_V2

def Emojify_V2(input_shape, word_to_vec_map, word_to_index):
    """
    Function creating the Emojify-v2 model's graph.
    
    Arguments:
    input_shape -- shape of the input, usually (max_len,)
    word_to_vec_map -- dictionary mapping every word in a vocabulary into its 50-dimensional vector representation
    word_to_index -- dictionary mapping from words to their indices in the vocabulary (400,001 words)

    Returns:
    model -- a model instance in Keras
    """
    
    ### START CODE HERE ###
    # Define sentence_indices as the input of the graph, it should be of shape input_shape and dtype 'int32' (as it contains indices).
    sentence_indices = Input(input_shape, dtype = 'int32')
    
    # Create the embedding layer pretrained with GloVe Vectors (≈1 line)
    embedding_layer = pretrained_embedding_layer(word_to_vec_map, word_to_index)
    
    # Propagate sentence_indices through your embedding layer, you get back the embeddings
    embeddings = embedding_layer(sentence_indices) 
    
    # Propagate the embeddings through an LSTM layer with 128-dimensional hidden state
    # Be careful, the returned output should be a batch of sequences.
    X = LSTM(128, return_sequences=True)(embeddings)
    # Add dropout with a probability of 0.5
    X = Dropout(0.5)(X)
    # Propagate X trough another LSTM layer with 128-dimensional hidden state
    # Be careful, the returned output should be a single hidden state, not a batch of sequences.
    X = LSTM(128, return_sequences=False)(X)
    # Add dropout with a probability of 0.5
    X = Dropout(0.5)(X)
    # Propagate X through a Dense layer with softmax activation to get back a batch of 5-dimensional vectors.
    X = Dense(5)(X)
    # Add a softmax activation
    X = Activation('softmax')(X)
    
    # Create Model instance which converts sentence_indices into X.
    model = Model(inputs=sentence_indices, outputs=X)
    
    ### END CODE HERE ###
    
    return model

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

X_train_indices = sentences_to_indices(X_train, word_to_index, maxLen)
Y_train_oh = convert_to_one_hot(Y_train, C = 5)

model.fit(X_train_indices, Y_train_oh, epochs = 50, batch_size = 32, shuffle=True)

 

 

- Summary:

    1) training set이 매우 작은 경우, word embedding을 사용하는 것이 도움이 된다. training set에 아예 없는 단어에도 작동할 수 있도록 만들어 준다.

    2) 케라스에서 sequence model을 학습시킬 때 다음과 같은 부분들을 명심하자

        1. mini-batch를 사용하기 위해서는 padding을 사용해 mini-batch안에 있는 모든 예시들이 같은 길이를 가지도록 만들어주자.

        2. Embedding() layer는 pretrained 된 값으로 초기화 될 수 있다.

        3. LSTM()은 return_sequence라는 flag를 가지고 있어 모든 hidden state를 리턴할 것인지, 아니면 마지막 state만 리턴 할 것인지를 정할 수 있다.

        4. LSTM()다음에 Dropout()을 사용해 네트워크를 정규화 시킬 수 있다.