Schedule

Please note that all times are listed in Lisbon Time (GMT+1)

The school is divided into 3h lectures with 30min break that dive into a specific topic and 1h practical talks by leading researchers in an area. We also include basic tutorials on the mathematical and programming (Python) fundamentals needed on the first day. Due to the fact that the school is being held remote, we have swapped the order of some lectures and practical talks to facilitate Q&A. The tentative schedule is shown below. You can also find it in Google Calendar (needs Google account) or as an ical zip that you can export to other calendar apps.

Students have direct access to the lectures, talks and labs through zoom and slack. Non students still have access to the stream here.

TUESDAY, JULY 21TH

09:00 – 10:30 Morning Session 1

BASIC TUTORIALS ON PROBABILITY THEORY AND LINEAR ALGEBRA (MARIO FIGUEIREDO)

11:00 – 12:30 Morning Session 2

INTRODUCTION TO PYTHON (LUIS PEDRO COELHO)

14:00 – 17:00 Afternoon session: Introduction to the Labs and Python
17:00 – Virtual Welcome reception

WEDNESDAY, JULY 22TH

09:00 – 12:30 Morning Lecture (30 min break at 10:30)

LECTURE 1: INTRODUCTION TO MACHINE LEARNING: LINEAR LEARNERS (ANDRE MARTINS)

  • Feature representations and linear decision boundaries
  • Naive Bayes, logistic regression, perceptron, SVMs
  • Online learning
  • Linear learning of non-linear models

14:00 – 17:00 Afternoon Labs: Linear Classifiers
17:00 – 20:30 Evening Lecture (30 min break at 18:30)

LECTURE 2: INTRODUCTION TO NEURAL NETWORKS (BHIKSHA RAJ)

  • Multi-layer perceptrons (Feed Forward networks)
  • Training with Backpropagation
  • Connectionist Computational Models
  • Universal Boolean Machines

THURSDAY, JULY 23TH

09:00 – 10:30 Morning Talk

PRACTICAL TALK: EXPLAINABILITY FOR NLP (ISABELLE AUGENSTEIN)

14:00 – 17:00 Afternoon Labs: Introduction to Deep Learning and Pytorch
17:00 – 20:30 Evening Lecture (30 min break at 18:30)

LECTURE 3: SEQUENCE MODELS (NOAH SMITH)

  • Markov models and hidden Markov models (HMMs)
  • Dynamic programming algorithms (Viterbi and sum-product)
  • Parameter learning (MLE and Baum-Welch/EM)
  • Finite state machines and finite state transducers

FRIDAY, JULY 24TH

09:00 – 10:00 Morning Talk

PRACTICAL TALK: GRAPH NEURAL NETWORKS IN NLP (IVAN TITOV)

14:00 – 17:00 Afternoon Labs: Sequence Models
17:00 – 18:00 Evening Talk

PRACTICAL TALK: TEXT REPRESENTATIONS FOR RETRIEVAL AND QUESTION ANSWERING (KRISTINA TOUTANOVA)

SATURDAY, JULY 25TH

09:00 – 12:30 Morning Lecture (30 min break at 10:30)

LECTURE 4: LEARNING STRUCTURED PREDICTORS (XAVIER CARRERAS)

  • From HMMs to CRFs: discriminative learning and features
  • Structured perceptron, structured SVMs and max-margin Markov networks
  • Training and optimization
  • Iterative scaling, L-BFGS, perceptron, MIRA, stochastic and batch gradient descent

14:00 – 17:00 Afternoon Labs: Structured Predictors
17:00 – 18:00 Evening Talk

PRACTICAL TALK: NATURAL LANGUAGE PROCESSING FOR THE REAL WORLD (SLAV PETROV)

SUNDAY, JULY 26TH

Free day!

MONDAY, JULY 27th

09:00 – 12:30 Morning Lecture (30 min coffee break at 10:30)

LECTURE 5: MODELING SEQUENTIAL DATA WITH RECURRENT NETWORKS (CHRIS DYER)

  • Recurrent Neural Networks
  • Learning challenges and solutions
  • Conditional sequence models
  • Learning with attention

14:00 – 17:00 Afternoon Labs: Sequence models in deep learning
17:00 – 18:00 Evening Talk

PRACTICAL TALK: QUESTION ANSWERING and GENERATION for EVALUATING SUMMARIZATION (KYUNGHYUN CHO)

TUESDAY, JULY 28th

09:00 – 12:30 morning Lecture (30 min coffee break at 10:30)

LECTURE 6: CAUSALITY (JONAS PETERS)

  • Causal Models
  • Structure Learning
  • Applications to Machine Learning

16:00 – 17:30 Discussion Panel: Careers in ML/NLP (Led by Kyunghyun Cho)

WEDNESDAY, JULY 29th

09:00 – 12:30 Morning Lecture (with 30 min coffee break at 10:30)

LECTURE 7: REINFORCEMENT LEARNING (STEFAN RIEZLER)

14:00 – 17:00 Afternoon Labs: Reinforcement Learning
17:00 – 18:00 Evening Talk

PRACTICAL TALK: PROCESSING SPOKEN LANGUAGE (MARI OSTENDORF)