Lecture 22 (30/5/2025): Open topics

Lecture 21 (29/05/2025): Word Sense Disambiguation and Semantic Role Labeling

 Word Sense Disambiguation and Semantic Role Labeling

Lecture 20 (23/5/2025): Introduction to Machine Translation

 Introduction to Machine Translation

Lecture 19 (22/05/2025): More on semantics, Knowledge graphs, Word Sense Disambiguation

Lecture 18 (16/5/2025): Introduction to Semantics, more on homework 2

Introduction to semantics, more on homework 2.

Lecture 17 (15/5/2025, 2h): homework 2 presentation

 Homework 2 presentation

Lecture 16 (8/5/2025): Reinforcement learning for NLP

 Reinforcement learning for NLP.

Lecture 15 (8/5/2025, 3h, L+R): Instruction tuning for LLMs, KV cache

Instruction tuning for LLMs, KV cache.

Lecture 14 (2/5/2025, 3h): Introduction to the Transformer (3): tokenization, decoding, LLMs

Introduction to the Transformer (3): tokenization, decoding, Large Language Models.

Lecture 13 (24/04/2025, 2h): Introduction to the Transformer (2), more on the encoder; Q&A for homework 1

More on the encoder, positional embeddings. Q&A for homework 1.

Lecture 12 (11/04/2025, 3h): Introduction to the Transformer (1), Transformer hands-on

Introduction to the Transformer architecture. Encoder, decoder. Self-attention. Cross-attention. Transformer hands-on.

Lecture 11 (10/04/2025, 2h): the Attention mechanism

Contextualized word representations. Introduction to the attention mechanism. 

Lecture 10 (04/04/2025, 3h): Perplexity, Wikidata hands-on

In-vitro vs. in-vivo evaluation. Introduction to perplexity. Relationship with probability of a sentence and cross-entropy. Wikidata hands-on session.

Lecture 9 (03/04/2025, 2h): More on language modeling, presentation of the homework

 

Lecture 8 (28/03/2025, 3h): introduction to probabilistic language modeling

What is a language model? N-gram models (unigrams, bigrams, trigrams), together with their probability modeling and issues. Chain rule and n-gram estimation.

Lecture 7 (27/03/2025, 2h): AI & the Parliament

Lecture with Vice-President Anna Ascani.

Lecture 6 (21/03/2025, 3h): More on word2vec, negative sampling

More on Word2Vec. Negative sampling: the skipgram case; changes in the loss function.

Lecture 5 (20/03/2025, 2h): Word embeddings, word2vec

Word representations. Word embeddings. Word2vec (CBOW and skipgram), PyTorch notebook on word2vec.

Lecture 4 (14/03/2025, 3h): first hands-on with PyTorch with language detection

Recap of the Supervised Learning framework, hands on practice with PyTorch on the Language Detection Model: tensors, gradient tracking, the Dataset and DataLoader class, the Module class, the backward step, the training loop, evaluating a model.

Lecture 3 (13/03/2025, 2h): Introduction to Supervised, Unsupervised & Reinforcement Learning

Introduction to Supervised, Unsupervised & Reinforcement Learning. The Supervised Learning framework. From real to computational: features extraction and features vectors. Feature Engineering and inferred features. PyTorch. Introduction to Colab notebooks and first part of the PyTorch hands-on.

Lecture 2 (07/03/2025, 3h): Logistic regression for NLP

Basics of Machine Learning for NLP. Probabilistic classification. Logistic Regression and its use for classification. Explicit vs. implicit features. The cross-entropy loss function.

Lecture 1 (06/03/2025, 2h): Introduction

 Introduction to the course. Introduction to Natural Language Processing: understanding and generation. What is NLP? The Turing Test, criticisms and alternatives. Tasks in NLP and its importance (with examples). Key areas and publication venues.

Ready? Set? GO!!!

Amazing news! This year we will work on developing our own, next-generation Large Language Model! Register here to attend the class! IMPORTANT: we will start on March 6 (February: no lecture, will be at AAAI).