Hugging Face

• Home (link)
• Transformers (link)
• Transformers - git (link)
• Datasets (link)
• Models (link)
• Inside Hugging Face’s Accelerate! (link)
• Introducing HF Accelerate (link)
• Hugging Face on PyTorch / XLA TPUs: Faster and cheaper training (link)
• Fine-Tune Wav2Vec2 for English ASR with HF-Transformers (link)
• The Partnership: Amazon SageMaker and Hugging Face (link)
• Fine-tuning a model on a text classification task - colab (link)
• Fine-tuning a model on a token classification task (link)
• HF + Comet (link)
• GerPT2-large (link)
• Multilingual Serverless XLM RoBERTa with HuggingFace, AWS Lambda (link)
• Transformers-based Encoder-Decoder Models (link)
• The ultimate guide to Transformer-based Encoder-Decoder Models (colab) (link) (link) (link) (link)
• Smaller, faster, cheaper, lighter: Introducing DistilBERT, a distilled version of BERT (link)

Attention, Transformer, Bert

• What Have Language Models Learned? (link)
• Simple Transformers (link)
• Comparing Transformer Tokenizers (link)
• Transformer Networks: A mathematical explanation why scaling the dot products leads to more stable gradients (link)
• 10 Things You Need to Know About BERT and the Transformer Architecture That Are Reshaping the AI Landscape (link)
• Bert Inner Workings (link)
• Summarization has gotten commoditized thanks to BERT (link)
• Retrieval Augmented Generation with Huggingface Transformers and Ray (link)
• How to Incorporate Tabular Data with HuggingFace Transformers (link)
• Extractive Text Summarization using Contextual Embeddings (link)
• How not to use BERT for Document Ranking (link)
• Conversational Summarization with Natural Language Processing (link)
• Transformers (link)
• ELECTRA — Addressing the flaws of BERT’s pre-training process (link)
• Encoder Decoder models in HuggingFace from (almost) scratch (link)
• Beyond BERT (link)
• Easy sentence similarity with BERT Sentence Embeddings using John Snow Labs NLU (link)
• TinyBERT — Size does matter, but how you train it can be more important (link)
• ELECTRA: Pre-Training Text Encoders as Discriminators rather than Generators (link)
• Poor Man’s BERT — Exploring Pruning as an Alternative to Knowledge Distillation (link)
• Data Extraction using Question Answering Systems (link)
• Understanding LongFormer’s Sliding Window Attention Mechanism (link)
• What Is The SMITH Algorithm? (link)
• BERT: Working with Long Inputs (link)
• XLNet outperforms BERT on several NLP Tasks (link)
• Text-to-Text Transfer Transformer (link)
• Transformer encoder - visualized (link)
• Emergent linguistic structure in artificial neural networks trained by self-supervision (link)
• Understanding Language using XLNet with autoregressive pre-training (link)
• Speeding up BERT (link)
• Pre-training BERT from scratch with cloud TPU (link)
• Dissecting BERT Part 1: Understanding the Transformer (link)
• Understanding BERT Part 2: BERT Specifics (link)
• deepset - bert (link)
• deepset - farm (link)
• How GPT3 Works - Visualizations and Animations (link)
• The Annotated GPT-2 (link)
• The Illustrated GPT-2 (Visualizing Transformer Language Models) (link)
• A Visual Guide to Using BERT for the First Time (link)
• The Illustrated BERT, ELMo, and co. (link)
• BERT - git google (link)
• The Illustrated Word2vec (link)
• The Annotated Encoder-Decoder with Attention (link)
• Seq2seq Models With Attention (link)
• How to code The Transformer in Pytorch (link)
• The Annotated Transformer (link)
• The Illustrated Transformer (link)
• Transformers from scratch (link)
• the transformer … “explained”? (link)
• PyTorch-Transformers (link)
• Comprehensive Language Model Fine Tuning, Part 1 (link)
• Which flavor of BERT should you use for your QA task? (link)
• Smaller, faster, cheaper, lighter: Introducing DistilBERT, a distilled version of BERT (link)
• Fastai with Transformers (BERT, RoBERTa, XLNet, XLM, DistilBERT) (link)
• Using SimpleTransformers for Common NLP Applications (link)
• minGPT - karpathy (link)
• A Quick Demo of Andrej Karpathy’s minGPT Play Char Demo (link)
• BERT Text Classification Using Pytorch (link)
• The Reformer - Pushing the limits of language modeling (link)
• Visual Paper Summary: ALBERT (A Lite BERT) (link)
• GPT-2 and the Nature of Intelligence (link)
• The Dark Secrets of BERT (link)
• Encoder-decoders in Transformers: a hybrid pre-trained architecture for seq2seq (link)
• Benchmarking Transformers: PyTorch and TensorFlow (link)
• Transformers Hugginface GitHub (link)
• Transformers - A collection of resources to study Transformers in depth. (link)
• XLNet, ERNIE 2.0, And RoBERTa: What You Need To Know About New 2019 Transformer Models (link)
• spaCy meets PyTorch-Transformers: Fine-tune BERT, XLNet and GPT-2 (link)

Misc

• Ultimate Guide To Text Similarity With Python - NewsCatcher (link)
• Unsupervised Text Summarization using Sentence Embeddings (link)
• Text Mining 101: A Stepwise Introduction to Topic Modeling using Latent Semantic Analysis (using Python) (link)
• An Introduction to Text Summarization using the TextRank Algorithm (link)
• The Language Interpretability Tool (LIT) (link)
• A guide to language model sampling in AllenNLP (link)
• Going Beyond SQuAD (Part 1) (link)
• GEM Benchmark - for Natural Language Generation (link)
• Learn Natural Language Processing the practical way (link)
• GLUE Benchmark (link) (link)
• Stanza – A Python NLP Package for Many Human Languages (link)
• nlp-tutorial (link)
• Self-host your HuggingFace Transformer NER model with Torchserve + Streamlit (link)
• jiant is an NLP toolkit (link)
• Transfer Learning for Natural Language Processing (Pact-Buch) (link)
• NER-Papers (link)
• Zero-Shot Learning in Modern NLP (link)
• NLP’s ImageNet moment has arrived (link)
• NLP Year in Review — 2019 (link)
• Current Issues with Transfer Learning in NLP (link)
• 74 Summaries of Machine Learning and NLP Research (link)
• Evaluation Metrics for Language Modeling (link)

NER

• Named Entity Recognition — Clinical Data Extraction (link)
• Training a spaCy NER Pipeline with Prodigy (link)
• Existing Tools for Named Entity Recognition (link)
• GermEval 2014 Named Entity Recognition Shared Task (link)
• A Named Entity Recognition Shootout for German - pdf (link)
• Named Entity Recognition and the Road to Deep Learning (link)
• A Named-Entity Recognition Program based on Neural Networks and Easy to Use (link)
• CRF Layer on the Top of BiLSTM 1 (link)
• CRF Layer on the Top of BiLSTM 2 (link)
• CRF Layer on the Top of BiLSTM 3 (link)
• CRF Layer on the Top of BiLSTM 4 (link)
• CRF Layer on the Top of BiLSTM 5 (link)
• CRF Layer on the Top of BiLSTM 6 (link)
• CRF Layer on the Top of BiLSTM 7 (link)
• CRF Layer on the Top of BiLSTM 8 (link) (link) (link)

Other

• link
• Haystack — Neural Question Answering At Scale (link)
• 5 NLP Libraries Everyone Should Know (link)
• link
• The NLP Pandect (link)
• Text Summary Papers (link)
• Transfer Learning in NLP - Folien Wolf Hugging Face (link)
• SOTA NLP (link)
• Ruder NLP Newsletter (link)
• Shuffling Paragraphs: Using Data Augmentation in NLP to Increase Accuracy (link)
• The Conversational Intelligence Challenge 2 (ConvAI2) (link)
• Workshop for Natural Language Processing Open Source Software (link)
• How to Train your Own Model with NLTK and Stanford NER Tagger? (for English, French, German…) (link)
• Supervised Word Vectors from Scratch in Rasa NLU (link)
• An overview of the NLP ecosystem in R (link)
• SNLI-decomposable-attention (link)
• A Review of the Neural History of Natural Language Processing (link)
• Eisenstein Buch (link)
• Holy NLP! Understanding Part of Speech Tags, Dependency Parsing, and Named Entity Recognition (link)
• NLP Architect by Intel AI LAB (link)
• TutorialBank: Learning NLP Made Easier (link)
• Comparing Sentence Similarity Methods (link)
• Text Embedding Models Contain Bias. Here’s Why That Matters (link)
• The Natural Language Decathlon (link)
• Joey NMT (link)

Spacy

• How to Fine-Tune BERT Transformer with spaCy 3 (link)