Text Handling: Matrix, Documents, Topics

Related lectures (28)

Page 2 of 3

Introduces deep learning concepts for NLP, covering word embeddings, RNNs, and Transformers, emphasizing self-attention and multi-headed attention.

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

Covers word embeddings, modeling word context and similarity in a low-dimensional space.

Explores the properties of invertible matrices, including unique solutions and linear independence.

Explains the construction of U, verification of results, and interpretation of SVD in matrix decomposition.

Covers modern Neural Network approaches to NLP, focusing on word embeddings, Neural Networks for NLP tasks, and future Transfer Learning techniques.

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

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

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

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