Natural Language Information Processing and Retrieval

Course Description

Natural Language Processing and Information Retrieval (IR) is an area that aims at understanding natural language and user information needs with the most relevant information. In this course we shall study how process text and natural language data and extract information from it to support multiple text related tasks.

This course starts by dissecting a text processing pipeline, and discusses the fundamental techniques currently used in information retrieval and NLP. Afterwards, the most relevant retrieval models, ranking and categorization methods and question answering techniques are discussed in detail.

This course includes extensive hands-on laboratories where key retrieval and NLP algorithms are examined. The goal is to strengthen students’ experimental analysis and critical thinking skills concerning search performance metrics and experimental results.

Objectives

Learn the concept of information relevance.
Learn how to parse and analyze text data.
Learn how to answer user queries and questions
Learn how to extract actionable information from text sources.
Analysis of experimental results.

Grading

Exam (40%) + Lab work (60% with three submissions)

Lab classes

Sept 15 - Lab guide 0 - Environment setup instructions + Jupyter Notebook + Lab 0 Data
Sept 22 - Lab guide 1 - Text processing, Words normalization, Types of Words Jupyter Notebook
Oct 29 - Project
Oct 6 - Lab guide 2 - Evaluation methods code here
Oct 13 - Project
Oct 20 - Lab guide 3 - Document classification Jupyter Notebook
Oct 27 - Project
Nov 3 - Project
Nov 10 - Project
Nov 17 - Lab guide 4 and 5 - Word embeddings Jupyter Notebook and BERT tutorial Jupyter Notebook
Nov 24 - Project

Project support

Batch CLS Embedding Extractor: Jupyter Notebook

Exercises (updated)

Lecturers

Joao Magalhaes ([email protected] - remove the ‘x’ character to send an email)