CMU Advanced NLP: Pre-training Methods
Explore advanced NLP concepts including multi-task learning, sentence embeddings, BERT variants, and language modeling objectives. Gain insights into cutting-edge techniques for natural language processing.
CMU Low Resource NLP Bootcamp 2020 - Neural Representation Learning
Explore neural representation learning in NLP, covering word and sentence representations, various approaches, and case studies on NNLM, GloVe, ELMO, BERT, RNN, CNN, and Transformers.
LLM Foundations - LLM Bootcamp
Explore foundational concepts of large language models, including machine learning basics, Transformer architecture, and notable LLMs. Gain insights into pretraining datasets and instruction tuning.
Large Language Models Simplified
Explore LLM concepts, prompt engineering, and augmented LLMs to build AI applications. Gain hands-on experience and expert insights into the cutting-edge world of Language Models.
Sentencepiece Tokenizer With Offsets for T5, ALBERT, XLM-RoBERTa and Many More
Implementación práctica del tokenizador Sentencepiece con offsets para modelos de transformers, enfocado en sistemas de preguntas y respuestas utilizando ALBERT.
Text Extraction From a Corpus Using BERT - Question Answering
Learn to extract text from tweets using BERT for sentiment analysis. Hands-on tutorial covers data preparation, model implementation, and evaluation for Kaggle competition.
Training Sentiment Model Using BERT and Serving It With Flask API
Learn to build and deploy a high-accuracy sentiment analysis model using BERT and Flask API, covering data preparation, model training, and serving the model for real-world applications.
Vector-Based Methods for Similarity Search - TF-IDF, BM25, SBERT
Explore three vector-based approaches for language comparison and document similarity: TF-IDF, BM25, and Sentence-BERT. Learn key techniques for building effective search engines in AI and machine learning.
TAPAS - Weakly Supervised Table Parsing via Pre-training
Explore TAPAS, an innovative approach to table parsing and question answering using pre-training and weak supervision, outperforming traditional semantic parsing models with a simpler architecture.
BERT- Pre-training of Deep Bidirectional Transformers for Language Understanding
Explore BERT's innovative approach to language representation, its bidirectional pre-training method, and its state-of-the-art performance across various natural language processing tasks.
Training BERT - Masked-Language Modeling
Explore BERT's masked-language modeling technique for NLP tasks. Learn how this innovative approach trains the model to predict masked tokens, enhancing its understanding of language context.
GPU-Acceleration for PyTorch on M1 Macs - Using with BERT
Explore GPU acceleration for PyTorch on M1 Macs, including installation, implementation with BERT, and best practices for training large language models on Mac hardware.
Deep Learning for Natural Language Processing
Explore NLP architectures, transformers, language models, and advanced techniques for text generation and embedding learning in this comprehensive deep learning lecture.
ALBERT - A Lite BERT for Self-Supervised Learning of Language Representations
Explore ALBERT, a streamlined BERT variant for efficient language representation learning, covering key innovations and performance benchmarks.
KDD2020 - Transfer Learning Joshi
Explore transfer learning via pre-training, focusing on BERT, span-based efficient pre-training, and ROBERTA. Discover advancements in contextualized representations and future directions in few-shot learning and non-parametric memories.
Building an Entity Extraction Model Using BERT
Learn to build an entity extraction model using BERT, transformers library, and PyTorch. Covers dataset preparation, configuration, training, and prediction for creating custom entity extraction solutions.
Spark NLP - State-of-the-Art Natural Language Processing at Scale
Discover scalable NLP techniques using Apache Spark, covering core algorithms, BERT embeddings, and multi-lingual challenges. Learn to build efficient pipelines for various NLP tasks through practical demonstrations.
Building a Pipeline for State-of-the-Art NLP Using Hugging Face Tools
Learn to build state-of-the-art NLP pipelines using Hugging Face tools. Explore tokenization, transformer networks, and various NLP tasks like sentiment analysis and question answering.
Natural Language Processing - Sam Bowman (NYU)
Explore recent progress in general-purpose language understanding models through GLUE and SuperGLUE benchmarks. Discuss evaluation techniques and future directions in NLP research.
Conversational AI with Transformer Models - Building Blocks and Optimization Techniques
Explore building conversational AI agents using transformer models, covering advantages over RNN/LSTM, knowledge distillation, and model compression techniques for efficient production deployment.
Fast and Accurate Deep Neural Networks Training
Exploring LARS and LAMB optimizers for scaling deep learning on supercomputers, enabling faster training and higher accuracy in AI applications across various industries.