BERT (language model)

Automated natural language processing software / From Wikipedia, the free encyclopedia

Dear Wikiwand AI, let's keep it short, summarize this topic like I'm... Ten years old or a College student

Bidirectional Encoder Representations from Transformers (BERT) is a transformer-based machine learning technique for natural language processing (NLP) pre-training developed by Google. BERT was created and published in 2018 by Jacob Devlin and his colleagues from Google.[1][2] In 2019, Google announced that it had begun leveraging BERT in its search engine, and by late 2020 it was using BERT in almost every English-language query. A 2020 literature survey concluded that "in a little over a year, BERT has become a ubiquitous baseline in NLP experiments", counting over 150 research publications analyzing and improving the model.[3]

The original English-language BERT has two models:[1] (1) the BERTBASE: 12 encoders with 12 bidirectional self-attention heads, and (2) the BERTLARGE: 24 encoders with 16 bidirectional self-attention heads. Both models are pre-trained from unlabeled data extracted from the BooksCorpus[4] with 800M words and English Wikipedia with 2,500M words.