Lectures related to Untitled | EPFL Graph Search

Vector Space Semantics (and Information Retrieval)

Explores the Vector Space model, Bag of Words, tf-idf, cosine similarity, Okapi BM25, and Precision and Recall in Information Retrieval.

Handling Text: Document Retrieval, Classification, Sentiment Analysis

Explores document retrieval, classification, sentiment analysis, TF-IDF matrices, nearest-neighbor methods, matrix factorization, regularization, LDA, contextualized word vectors, and BERT.

Embedding Models: Concepts and Retrieval

Covers embedding models for document retrieval, latent semantic indexing, SVD, and topic models.

Document Retrieval and Classification

Covers document retrieval, classification, sentiment analysis, and topic detection using TF-IDF matrices and contextualized word vectors like BERT.

Word Embeddings: Models and Applications

Explores word embeddings, models like CBOW and Skipgram, Fasttext, Glove, subword embeddings, and their applications in document search and classification.

Binary Sentiment Classifier Training

Covers the training of a binary sentiment classifier using an RNN.

Text Handling: Matrix, Documents, Topics

Explores text handling, focusing on matrices, documents, and topics, including challenges in document classification and advanced models like BERT.

Lexical Semantics

Explores lexical semantics, word sense, semantic relations, and WordNet, highlighting applications in language engineering and information retrieval.

Neural Word Embeddings: Learning Representations for Natural Language

Covers neural word embeddings and methods for learning word representations in natural language processing.

Word Embeddings: Introduction and Applications

Introduces word embeddings, explaining how they capture word meanings based on context and their applications in natural language processing tasks.

Neural Word Embeddings

Introduces neural word embeddings and dense vector representations for natural language processing.

Text Processing: Large Digital Text Collections Analysis

Delves into the processing of large digital text collections, exploring hidden regularities, text reuse, and TF-IDF analysis.

Language Models: From Theory to Computation

Explores the mathematics of language models, covering architecture design, pre-training, and fine-tuning, emphasizing the importance of pre-training and fine-tuning for various tasks.

Information Retrieval Basics

Introduces the basics of information retrieval, covering document representation, query expansion, and TF-IDF for document ranking.

Latent Semantic Indexing: Concepts and Applications Log in to Mediaspace to watch this video

Explores Latent Semantic Indexing, a technique for mapping documents into a concept space for retrieval and classification.

Latent Semantic Indexing Log in to Mediaspace to watch this video

Covers Latent Semantic Indexing, word embeddings, and the skipgram model with negative sampling.

Information Retrieval Indexing: Latent Semantic Indexing Log in to Mediaspace to watch this video

Explores Latent Semantic Indexing in Information Retrieval, discussing algorithms, challenges in Vector Space Retrieval, and concept-focused retrieval methods.

Word Embeddings: Models and Learning Log in to Mediaspace to watch this video

Explores word embeddings, context importance, and learning algorithms for creating new representations.

Optimization in Machine Learning Log in to Mediaspace to watch this video

Explores optimization techniques, word embeddings, and recommendation systems in machine learning.

Text Models: Word Embeddings and Topic Models Log in to Mediaspace to watch this video

Explores word embeddings, topic models, Word2vec, Bayesian Networks, and inference methods like Gibbs sampling.