Giter VIP home page Giter VIP logo

dl-for-chatbot's Introduction

Deep leaning for Chatbot Developers

Contents

Day 01 Introduction to Chatbot (slideshare)

  • Introduction to NLP/Chatbot
  • Overview of Korean/English NLP Toolkits/Datasets
  • Tutorial (code)
    • Introduction to spaCy / gensim / konlpy / other Korean toolkits
    • Sentiment classification via TF-IDF (scikit-learn)
    • Chatbot Pipelining / Serving via Kakaotalk (flask) / Slack (slacker)

Day 02 Text Classification with CNN/RNN (slideshare)

  • CNN for text classification
    • Word CNN / Dynamic CNN / Char CNN / Very Deep CNN
  • RNN for text classification
    • Bidirectional RNN / Recursive NN / Tree LSTM / Dual Encoder LSTM
  • Advanced CNN/RNN architectures
    • QRNN / SRU / ByteNet / SliceNet / LSTM-CNNs-CRF
  • Tutorial (code)
    • Word-CNN for sentiment analysis
    • PyTorch Style Guide
    • TorchText Tutorial

Day 03 Conversation Modeling with Seq2Seq / Attention (slideshare)

  • Seq2Seq models for conversation modeling
    • Seq2Seq / Neural Conversation model / Diversity-prompting objective: MMI
  • Advanced Seq2Seq architectures
    • Show and Tell / HRED / VHRED / Personal based Neural Conversation model / Contextualized Word Vectors (CoVe)
  • Attention mechanism
    • Bahdanau / Luong
    • Global / Local
  • Advanced Attention architectures
    • Show, Attend and Tell / Pointer Networks / CopyNet / BiDAF / Transformer
  • Tutorial (code)
    • Seq2Seq with Attention for Machine Translation

Day 04 QA with External Memory (slideshare)

  • QA with External Memory
    • Memory Networks / End-to-End Memory Networks / Key-value Memory Networks / Neural Turing Machines
  • Advanced Memory architectures
    • DNC / Life-long memory Modules / Context-Sequence Memory Networks
  • Advanced Dialogue Architectures
    • MILABOT / Dialog based language learning / End-to-End Goal Oriented Dialog / Deep RL / Adversarial
  • Tutorial (code)
    • End-to-End Memory Networks for Question Answering (bAbI)

Dependencies

Python 3

  • Codes are written in Anacodna Python 3.6.
  • Package management via Conda or virtualenv is recommended.

ML / NLP

  • PyTorch
  • TorchText
  • spaCy
  • sckit-learn
  • gensim
  • konlpy (requires Jpype3)

Interactive / DataFrame / Plot

  • jupyter
  • pandas
  • matplotlib

Kakaotalk / Slack Bot

  • flask
  • websocket-client
  • beautifulsoup4
  • slacker

dl-for-chatbot's People

Contributors

j-min avatar zebehn avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

dl-for-chatbot's Issues

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.