Master in Data Science (MDS)

Mining Unstructured Data - Spring 2024

Instructors

Jordi Turmo (coordinator), turmo@cs.upc.edu
Office: Omega-321, Campus Nord UPC
Salvador Medina, salvador.medina.herrera@upc.edu
Office: Omega-S106, Campus Nord UPC
Carlos Escolano (laboratory), carlos.escolano@upc.edu
Office: Omega-S106, Campus Nord UPC
Bardia Rafieian (laboratory), bardia.rafieian@upc.edu
Office: 8.7, Campus Diagonal UPC

Sessions

	Date	Content	Lecturer
Week 1	February 12nd	Introduction to MUD	Jordi
Week 1	February 13th	Lab Session 1 Introduction to laboratory Task data & other stuff	Carlos / Bardia
Week 2	February 19th	Document structure and language	Jordi
Week 2	February 20th	Lab Session 2 Guides and code for task 1 (Document structure and language)	Carlos / Bardia
Week 3	February 26th	Words: PoS Tagging	Jordi
Week 3	February 27th	Lab Session 3	Carlos / Bardia
Week 4	March 4th	Words: Lexical Semantics	Jordi
Week 4	March 5th	Lab Session 4 Exercise of WordNet similarities Link to the colab code	Carlos / Bardia
Week 5	March 11th	Word Sequence: Named Entities and Noun Phrases Exercises about features for word sequence recognition	Jordi
Week 5	March 12th	Lab Session 5 Guidelines for task 2 (ML-based NERC) Code for task 2	Carlos / Bardia
Week 6	March 18th	Sentence: Constituent Parsing Exercises about constituent parsing	Jordi
Week 6	March 19th	Lab Session 6	Carlos / Bardia
	March 25th and 26th	No class (Bank Holidays)
Week 7	April 1st	No class (Bank Holidays)
Week 7	April 2nd	Lab Session 7	Carlos / Bardia
	April 8th and 9th	No class - FIB midterm exam week (No MUD midterm exam, though)
Week 8	April 15th	Sentence: Dependency Parsing Exercises about dependency parsing	Jordi
Week 8	April 16th	Lab Session 8 Guidelines and code for task 3 (ML-based DDI) Code for task 3	Carlos / Bardia
Week 9	April 22nd	Discussion/Review/Exercises	Jordi
Week 9	April 23th	Lab Session 9	Carlos / Bardia
Week 10	April 29th	Word Embeddings Exercises about Word Embeddings	Salvador
Week 10	April 30th	Lab Session 10 Guidelines and code for task 4 (NN-based NER)	Carlos / Bardia
Week 11	May 6th	Word Classification Exercises about Word Classification	Salvador
Week 11	May 7th	Lab Session 11	Carlos / Bardia
Week 12	May 13th	Recurrent NN Language Models Exercises about RNNs	Salvador
Week 12	May 14th	Lab Session 12 Guidelines and code for task 5 (NN-based DDI)	Carlos / Bardia
Week 13	May 20th	No class (Local Holidays). Moved to the 21th
Week 13	May 21st	Transformers Exercises about transformers	Salvador
Week 14	May 27th	Large language models	Salvador
Week 14	May 28th	Lab Session 13	Carlos / Bardia

Important dates

March 4th: Delivery of Doc. structure and language report (lab task 1)

April 29th: Delivery of ML-based report (lab tasks 2 and 3)

June 11st: Delivery of NN-based report (lab tasks 4 and 5)

June 17th: Final exam

Solved Exercises

Exercises about Features for Word Sequence Recognition

Exercises about Constituent Parsing

Exercises about Dependency Parsing

Exercises about Word Embeddings

Exercises about Word Classification

Exercises about RNNs

Resources

Complementary Readings

Alexander Clark, Chris Fox, Shalom Lappin (eds.)
The Handbook of Computational Linguistics and Natural Language Processing
Blackwell Handbooks in Linguistics, John Wiley & Sons, 2012.
R. Dale, H. Moisl, H.Somers (eds.)
Handbook of Natural Language Processing
Marcel Dekker, New York, 2000.
Nitin Indurkhya, Fred J. Damerau
Handbook of Natural Language Processing, Second Edition
Chapman & Hall/CRC Machine Learning & Pattern Recognition, 2010.
D. Jurafsky, James H. Martin
Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition
Prentice Hall, Upper Saddle River, N.J., 2017 (online version)
C. Manning, H. Schütze
Foundations of Statistical Natural Language Processing
MIT Press, Cambridge, Mass., 1999.
R. Mitkov (ed.)
The Oxford Handbook of Computational Linguistics
Oxford University Press, 2004.

Software

Language Processing

Machine Learning / Deep Learning

External Knowledge

Word Embeddings

Utilities