Lectures related to Neural Word Embeddings

Neural Word Embeddings: Learning Representations for Natural Language

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

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

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.

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.

Document Retrieval and Classification

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

Text Handling: Matrix, Documents, Topics

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

Language Models: Fixed-context and Recurrent Neural Networks

Discusses language models, focusing on fixed-context neural models and recurrent neural networks.

Pretraining: Transformers & Models

Explores pretraining models like BERT, T5, and GPT, discussing their training objectives and applications in natural language processing.

Pretraining Sequence-to-Sequence Models: BART and T5

Covers the pretraining of sequence-to-sequence models, focusing on BART and T5 architectures.

Contextual Representations: ELMO and BERT Overview

Covers contextual representations in NLP, focusing on ELMO and BERT architectures and their applications in various tasks.

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.

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.

Modern NLP: A Simple Neural Classifier

Introduces the basics of modern NLP, covering word embeddings, neural models, and tasks like sequence labeling and text generation.

Deep Learning for Question Answering

Explores deep learning for question answering, analyzing neural networks and model robustness to noise.

Coreference Resolution

Delves into coreference resolution, discussing challenges, advancements, and evaluation methods.

Handling Text Data: Document Retrieval and Classification

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

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.

Deep Learning for NLP Log in to Mediaspace to watch this video

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

Word Embeddings: Modeling Word Context and Similarity Log in to Mediaspace to watch this video

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

Natural Language Processing: Understanding Transformers and Tokenization Log in to Mediaspace to watch this video

Provides an overview of Natural Language Processing, focusing on transformers, tokenization, and self-attention mechanisms for effective language analysis and synthesis.