Natural Language Processing

Introduction to Statistical NLP Techniques, Word Embeddings, Introduction to Sequential models, NLP Applications


Introduction to Statistical NLP Techniques

1.       Introduction to NLP

2.       Pre-processing in NLP-Tokenization, Stop words, Normalisation,stemg and lemmatization

3.       Pre-processing in NLP-Bag of words, TF-IDF as features

4.       Language Models Probabilistic models, N-gram model and channel model

5.       Hands On Lab

1.       Hands-on demo_NLP Basics with NLTK

2.       BasicNLPv1.ipynb

3.       Practice Exercise 1.ipynb

Word Embeddings

1.       Word2Vectors

2.       Glove

3.       Hands-on demo : Word Embeddings

4.       Applications : POS tagging, NER

5.       Hands-on demo : POS tagging with NLTK

6.       Hands-on demo : TF-IDF with NLTK

7.       Codes and Datasets

1.       Word2Vec Example.ipynb

2.       TFIDF_Example_v1.ipynb

3.       POS Tagging with NLTK v1.ipynb

4.       Link to the codes and datasets for week 10

5.       Practice Exercise 2.ipynb

Introduction to Sequential models

1.       Introduction to sequential models

2.       Introduction to RNN

3.       Introduction to LSTM

4.       LSTM Forward Pass

5.       LSTM Backprop through time

6.       Hands-on demo in Keras: POS tagger using LSTM

1.       POS Tagger LSTM v1.ipynb

2.       ner_dataset.csv


NLP Applications

1.       LSTM Applications: Sentiment Analysis, Sentence generation, Machine Translation

2.       Advanced LSTM Structures

3.       Hands-on Demo in Keras: Machine Translation

1.       EncoderDecoderAttentionV3.ipynb

2.       mar.txt

4.       Hands-on demo in Keras: Sentiment Analysis

1.       LSTM Sentiment Analysis Kaggle v1.ipynb

2.       Sentiment.csv

Project Work

  1. DLCP Project 3 Brief.pdf
  2. DLCP_Project_3_NLP_Updated.ipynb