Giter VIP home page Giter VIP logo

nlp-tensorflow's Introduction

NLP Tutorial with Deep Learning using tensorflow


1. Install requirements

$ pip install -r requirements.txt

2. 01-sentiment_analysis

네이버 영화 평점 데이터를 이용하여 여러 딥러닝 모델을 비교해 볼 수 있습니다.
다양한 컴퓨터 사양으로 테스트 해 볼 수 있도록 데이터셋을 크기에 따라 세 가지를 두었습니다.

Contents

  1. Data Process
  2. Logistic Regression
  3. Feed Forward Neural Network
  4. RNN: with rnn tensorflow API explanation
  5. LSTM: uni-directional LSTM, bi-directional LSTM, deep-bi-directional LSTM
  6. CNN
  7. POS: with konlpy Twitter API
  8. Morphs: with konlpy Twitter API
  9. word2vec: with gensim API
  10. doc2vec: with gensim API
  11. Every model is defined at models

3. 02-nlp_application

딥러닝 모델을 이용하여 사용자의 입력을 받아 [감성분석, 삼행시만들기, 대화하기]를 테스트 할 수 있습니다.
훈련된 모델이 같이 들어있어 train 없이 바로 test 할 수 있으며, gpu 없이 train 할 시, 시간이 오래 걸릴 수 있습니다.

train

$ python train.py

implementation

$ python test.py

4. Notice

  1. 02-nlp_application/01-Sentiment 의 경우, models 폴더 안 model-31000.zip 파일의 압축을 풀어주어야 train 없이 바로 test 할 수 있습니다.

ubuntu/mac: how to unzip in command line

$ zip -FF model-31000.zip --out model-31000-full.zip
$ unzip model-31000-full.zip

  1. 모든 데이터는 한국어로 이루어져 있습니다.

  2. konlpy 설치는 http://konlpy.org/en/v0.4.4/install/ 를 참조하세요.

nlp-tensorflow's People

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

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.