NLP - Tutorial

Repository to show how NLP can tacke real problem. Including the source code, dataset, state-of-the art in NLP

• NLP Preprocessing
  • Part 1: Word Tokenization Medium Github
  • Part 2: Part of Speech Medium Github
  • Part 3: Lemmatization Medium Github
  • Part 4: Stemming Medium Github
  • Part 5: Stop Words Medium Github
  • Part 6: Sentence Tokenization Medium Github
  • Part 7: Phrase Word Recognition
• Infomration Retrieval
  • Pattern-based Recognition Medium
  • Lexicon-based Recognition Medium
  • off-the-shelf Named Entity Recognition (NER) Medium Github
  • Custom Named Entity Recognition (NER)
• Text Summarization
  • Extractive Approach Medium Github
  • Abstractive Approach
• Distance Measurement
  • Euclidean Distance, Cosine Similarity and Jaccard Similarity Medium Github
  • Word Mover's Distance (WMD) Medium Github
• Vector Representation
  • Bag of Word (BoW) Medium Github
  • Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) Medium Github
  • Character Embedding Medium Github
  • Word Embedding (Word2Vec, GloVe, fastText) Medium Github
  • LDA2vec
  • Doc2Vec (doc2vec)
  • Context Vectors (CoVe)
• Others
  • Negative Sampling and Hierarchical Softmax
• Model Interpretation
  • Skater, LIME and ELI5 Medium Github
  • SHapley Additive exPlanations (SHAP) Medium Github
• Myth
  • Using Deep Learning can resolve all problem? Medium Kaggle