Neural Networks with Keras Cookbook

Putting it all together

In the previous section, we built two models, where the first model predicts the entities in a query and the second model extracts the intent of queries. 

In this section, we will define a function that takes a query and converts it into a structured format:

1. Preprocess the new input text so that it can be passed to the model:

def preprocessing(text):     text2 = text.split()     a=[]     for i in range(len(text2)):         a.append(sentence_word_to_int[text2[i]])     return a

2. Pre-process the input text to convert it into a list of word IDs:

text = "BOS i would fly from boston to dallas EOS"

indexed_text = preprocessing(text)padded_text=np.zeros(50)padded_text[:len(indexed_text)]=indexed_textpadded_text=padded_text.reshape(1,50)

The preceding ...