用 seq2seq 建立聊天机器人-学习如何使用 TensorFlow 建立聊天机器人。
Chatbots with Seq2Seq-Learn to build a chatbot using TensorFlow
Last year, Telegram released its bot API, providing an easy way for developers, to create bots by interacting with a bot, the Bot Father. Immediately people started creating abstractions in nodejs, ruby and python, for building bots. We (Free Software Community) created a group for interacting with the bots we built. I created Myshkin in nodejs that answers any query with a quote. The program uses the linux utility fortune, a pseudorandom message generator. It was dumb. But it was fun to see people willingly interact with a program that I’ve created. Someone made a Hodor bot. You probably figured out what it does. Then I encountered another bot, Mitsuku which seemed quite intelligent. It is written in AIML (Artificial Intelligence Markup Language); an XML based “language” that lets developers write rules for the bot to follow. Basically, you write a PATTERN and a TEMPLATE, such that when the bot encounters that pattern in a sentence from user, it replies with one of the templates. Let us call this model of bots, Rule based model.