BERT

Rarity: Uncommon

A topic a little better known than average, read and translated beyond its own country.

Rarity follows how well known the article is: its views on the French and English Wikipedia over a year, and the number of languages it exists in.

At a glance

Class

Notion

Domain

Science and technology

In collections

Nobody has pulled it yet.

What Wikipedia says

Bidirectional encoder representations from transformers (BERT) is a language model introduced in October 2018 by researchers at Google. It learns to represent text as a sequence of vectors using self-supervised learning. It uses the encoder-only transformer architecture.

Excerpt from the Wikipedia article “BERT (language model)”, under the CC BY-SA 4.0 license. Read the article on Wikipedia