Giter VIP home page Giter VIP logo

rasa_chatbot's Introduction

rasa_chatbot

A Chinese task oriented chatbot in IVR(Interactive Voice Response) domain(电信ivr领域, 中文), Implement by rasa nlu and rasa core. This is a demo with toy dataset.

install dependency:

dir tree

rasa_chatbot/
├── chat_detection            # chat domain detection, todo now
├── data
│   ├── mobile_nlu_data.json  # rasa nlu train data
│   ├── mobile_story.md       # rasa core train data
│   └── total_word_feature_extractor.dat  # mitie word vector feature
├── tools                     # tools for data process
├── __init__.py               # init file
├── httpserver.py             # rasa nlu httpserver
├── bot.py                    # ivr bot main script.
├── mobile_domain.yml         # rasa core domain file
├── mobile_nlu_model_config.json  # rasa nlu config file
├── models                    # directory to save trained models
└── README.md                 # readme file

train nlu model

python bot.py train-nlu

train dialogue

python bot.py train-dialogue

train dialogue in online mode

python bot.py online_train

test

Run command below:

python bot.py run

Example1:

Bot loaded. Type a message and press enter : 
YOU:你是谁
BOT:您好!,我是机器人小热,很高兴为您服务。
YOU:我想看一下消费情况
BOT:您想查询哪个月的消费?
YOU:十月份的
BOT:好,请稍等
BOT:您好,您十月份共消费二十八元。
YOU:好谢谢
BOT:您开心我就开心
BOT:您还想干什么
YOU:没什么了
BOT:Bye, 下次再见

Example2:

Bot loaded. Type a message and press enter : 
YOU:给我看看我上月用了多少话费
BOT:好,请稍等
BOT:您好,您上月共消费二十八元。
BOT:您还想干什么

train word vector

You can train your own MITIE model using following method:

$ git clone https://github.com/mit-nlp/MITIE.git
$ cd MITIE/tools/wordrep
$ mkdir build
$ cd build
$ cmake ..
$ cmake --build . --config Release
$ ./wordrep -e /path/to/your/folder_of_cutted_text_files

/path/to/your/folder_of_cutted_text_files above is a directory path in which has word cutted data files to train. This process may cost one or two days.

rasa_chatbot's People

Contributors

zqhzy avatar

Watchers

James Cloos avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.