C#/.net>> ml-deep-learning-keras-novel>> 返回
项目作者： erdiolmezogullari

项目描述 ：
Which Novel Do I Belong To? - Deeplearning (LSTM) on top of Keras (Tensorflow)
高级语言： Jupyter Notebook
项目地址: git://github.com/erdiolmezogullari/ml-deep-learning-keras-novel.git


Image

Which novel do I belong To?

Problem Data Methods Libs Link
NLP Text Deep Learning - LSTM, Word2Vec Sklearn, Keras, Gensim, Pandas, Seaborn https://github.com/erdiolmezogullari/ml-deep-learning-keras-novel

If you want to see the further ML projects, you may visit my main repo: https://github.com/erdiolmezogullari/ml-projects

This project is related to text classification problem that we tackled with Deeplearing (LSTM) model, which classifies given arbitrary paragraphes collected over 12 different novels randomly, above: 

  1. 0. alice_in_wonderland
  2. 1. dracula
  3. 2. dubliners
  4. 3. great_expectations
  5. 4. hard_times
  6. 5. huckleberry_finn
  7. 6. les_miserable
  8. 7. moby_dick
  9. 8. oliver_twist
  10. 9. peter_pan
  11. 10. talw_of_two_cities
  12. 11. tom_sawyer

In other words, you can think about those novels are our target classes of our dataset.
To distinguish actual class of paragraph, the semantic latent amongst paragraphes would play an important role. Therefore, We used Deeplearing (LSTM) on top of Keras (Tensorflow) after creating an embedding matrix by Gensim's word2vec.

If there is any semantic latent amongst sentences in corresponding paragraph,
We think about similar paragraphes were collected from same resources (novels) most likely.