Introduction

NLP pipeline with spaCy.
TF-IDF.
Text analysis with scikit-learn.

Language models and text classification

Language models: definition, algorithms, and evaluation.
Text classification: algorithms and feature engineering.

Topic modeling

Non-negative matrix factorization (NMF).
Latent Semantic Indexing (LSI).
Latent Dirichlet Allocation (LDA).

Word vectors

Distributional hypothesis.
Word2Vec algorithm.

Word vectors - 2

GloVe algorithm. Typical use cases of word vectors in NLP tasks. Word2Vec in recommendation systems. Analysis of graphs using Node2Vec.

Recurrent Neural Networks

Vanilla RNN. Neural Language Models.

Recurrent Neural Networks - 2

Vanishing gradients.
LSTM and GRU.
Bidirectional RNN.

Contextual Word Embeddings

ELMo and ULM-Fit

Attention and transformers

Text mining in the wild

Structured datasets.
Public APIs and semi-structured datasets. Using metadata and link information. HTML parsing.

NLP libraries and models

FastText.
More about spaCy and GenSim.
Pre-trained transformers.

Neural Networks

Feedforward neural networks.
Computation graph and back propagation. Optimization methods.

Case study: text summarization
(example project)

Case study: news aggregator

Final project session