Master in Data Science (MDS)

Mining Unstructured Data - Spring 2022

Instructors


Sessions

Date Content Lecturer
Week 1 February 16th Document structure and language
Jordi
February 15th Lab Session 1 :
Introduction to MUD
Task description
Task data & other stuff
Carlos
Week 2 February 23th Words: PoS Tagging
Jordi
February 22th No Lab Session
Week 3 March 2th Words: Lexical Semantics Jordi
March 1th Lab Session 2 :
Guides and code for task 1 (Document structure and language)
Carlos
Week 4 March 9th Word Sequence: Named Entities and Noun Phrases
Exercises about features for word sequence recognition
Jordi
March 8th No Lab Session
Week 5 March 16th Sentence: Constituent Parsing
Exercises about constituent parsing
Jordi
March 15th Lab Session 3 :
Guidelines and code for task 2 (ML-based NERC)
Carlos
Week 6 March 23th Sentence: Dependency Parsing
Exercises about dependency parsing
Jordi
March 22nd No Lab Session
Week 7 March 30th Discussion/Review/Exercises Jordi
March 29th Lab Session 4 :
Guidelines and code for task 3 (ML-based DDI)
Carlos
April 5th and 6th No class - FIB midterm exam week
(No MUD midterm, though)
April 12th and 13th No class (spring break)
Week 8 April 20th Word Embeddings
Exercises about Word Embeddings
Javier
April 19th No Lab Session
Week 9 April 27th Word Classification
Exercises about Word Classification
Javier
April 26th Lab Session 5 :
Guidelines and code for task 4 (NN-based NER)
Carlos
Week 10 May 4th Recurrent NN Language Models
Exercises about RNNs
Javier
May 3th No Lab Session
Week 11 May 11th Transformers
Exercises about transformers
-->
Javier
May 10th Lab Session 6 :
Guidelines and code for task 5 (NN-based DDI)
Carlos
Week 12 May 18th On the applicability of deep learning models Javier
May 17th No Lab Session
Week 13 May 25th Discussion/Review Javier
May 24th Lab Session 7 :
Consulting
Carlos

Important dates

March 14th: Delivery of Doc. structure and language report (lab task 1)
April 25th: Delivery of ML-based report (lab tasks 2 and 3)
June 13th: Delivery of NN-based report (lab tasks 4 and 5)
June 7th: Final exam

Resources

Complementary Readings

Software