根据句子生成Emoji表情

参考资料：
Coursera-Sequence Models 第二周作业2

• 作业任务
  将句子映射到emoji表情
  "Congratulations on the promotion! Lets get coffee and talk. Love you!"
  "Congratulations on the promotion! 👍 Lets get coffee and talk. ☕️ Love you! ❤️"

• 数据集

  
  

• 第一个模型Emojifier-V1
  很简单的模型，对词向量进行平均，然后经过一个隐藏层的神经网络，softmax输出

  
  
  
  

  计算平均

# 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,)
    """
    
    ### START CODE HERE ###
    # 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(shape=word_to_vec_map[words[0]].shape)
    
    # 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)
    
    ### END CODE HERE ###
    
    return avg

这个模型的准确率：
Train set accuracy 97.7
Test set accuracy 85.7
测试结果：

i adore you ❤️
i love you ❤️
funny lol 😄
lets play with a ball ⚾
food is ready 🍴
not feeling happy 😄

但是不能预测好not feeling happy

• confusion_matrix

print(Y_test.shape)
print('           '+ label_to_emoji(0)+ '    ' + label_to_emoji(1) + '    ' +  label_to_emoji(2)+ '    ' + label_to_emoji(3)+'   ' + label_to_emoji(4))
print(pd.crosstab(Y_test, pred_test.reshape(56,), rownames=['Actual'], colnames=['Predicted'], margins=True))
plot_confusion_matrix(Y_test, pred_test)

• 改进模型Emojifier-V2: Using LSTMs in Keras

  
  
  
  

  因为句子的长度不同，所以需要padding和truncate到相同的长度。
  这个模型可以应对反义词汇。