Hands-On Natural Language Processing with Python

Interacting with the chatbot

Finally, we can interact with our chatbot by following the framework described in the previous sections. After each user utterance, we ask the memory network to predict a response based on the conversation history and the utterance. Then, the utterance and response are appended to the conversation history and we can enter an utterance once again:

    def interactive_mode(self):        facts = []        utterance = None        response = None        turn_count = 1        while True:            line = input("==> ").strip().lower()            if line == "exit":                break            if line == "restart":                facts = []                turn_count = 1                print("Restarting dialog...\n")                continue            utterance = tokenize(line)            data = [(facts, utterance, -1)]            # Vectorize data and make prediction f, q, a = vectorize_data(data, ...