NLP-2023

A series of notebooks that constitute the coding assignments for Natural Language Processing subject in Artificial Intelligence degree (UAB).

Assignments:

1. Basic-Text-Processing-Exercises:

Description of exercises:

1, 2: RegEx

3, 4, 5: Minimum Edit Distance

6: ELIZA with regEx

Notebook:

Introduction to NLP.

2. Introduction to nltk. basic python for NLP.

Description of exercises:

1-6: Experiment with tree parsing in Context free grammars, both probabilistic and non-probabilistic

Notebook:

NLTK library

3. Simple language models & Language modeling with pytorch

Simple language models: ngrams, MLE, laplace, stupid backoff

Neural language models (NNLM)

Real word spellchecker

4. Sequence Labelling (HMM & CRF)

Sequence labeling and NER with a simple baseline algorithm

Sequence labeling and NER with HiddenMarkov Models (HMM) and Conditional Random Fields (CRF)

5. Vector Space models (PMI, PPMI, LSA...)

Vector Space models full notebook