Course : Natural Language Processing (MSc CS & MSc ISDS)

Course code : INF210

Natural Language Processing (MSc CS & MSc ISDS)

INF210  -  Ion Androutsopoulos

Documents
Root directory slides_2026_27   The slides of 2026-27.
Cancel
First Name Size Date
nlp_slides_part00_introduction.pdf
Introduction and course organization.
2.65 MB 10/1/26, 5:19 PM
nlp_slides_part01_ngrams.pdf
n-gram language models, estimating probabilities from corpora, entropy, cross-entropy, perplexity, greedy, top-k, top-p sampling, beam search decoding, context-aware spelling correction, sub-word tokenizers.
4.05 MB 10/13/26, 6:26 PM
nlp_slides_part02_text_classification_with_linear_models.pdf
Representing documents as bags of words. Boolean and TF-IDF features. Feature selection using information gain. Linear and logistic regression, stochastic gradient descent. Evaluating classifiers with precision, recall, F1, AUC. Practical advice and diagnostics for text classification with supervised machine learning. Obtaining word embeddings from PMI scores, using SVD for dimensionality reduction.
3.65 MB 10/9/26, 3:05 PM
nlp_slides_part03_text_classification_with_mlps.pdf
Multi-Layer Perceptrons (MLPs), computation graphs, backpropagation. Dropout, batch/layer/RMS normalization. MLPs for text classification, regression, token classification (e.g., for POS tagging, named entity recognition). Pre-training word embeddings, Word2Vec. Advice for training large neural networks.
2.37 MB 10/22/26, 2:19 PM