• If you find this repository helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
  • BERT, also known as Bidirectional Encoder Representations from Transformers, is an artificial intelligence (AI) approach to understanding natural language.
  • Searching for the tutorial didn’t help me much, I had to gather the knowledge in little pieces to get a full picture of BERT.
  • BERT is a transformer-based machine learning technique for natural language processing (NLP) pre-training developed by Google.
  • BERT is designed to help computers understand the meaning of ambiguous language in text by using surrounding text to establish context.
  • BERT’s key technical innovation is applying the bidirectional training of Transformer, a popular attention model, to language modelling.
  • BERT was trained on a large dataset (you'll hear BERT called a large language model or LLM quite frequently) and as such has general language representation.
  • BERT, short for Bidirectional Encoder Representations from Transformers, is a machine learning (ML) framework for natural language processing.
  • So how is BERT different from all the models that were released in 2018? Well, to answer that question we need to understand what BERT is and how it works.