thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Intermediate

BERT

Bidirectional Encoder Representations from Transformers: Google's 2018 encoder-only model pretrained with masked language modeling.

Definition

BERT learns context from both directions and is fine-tuned for classification, NER and question answering. Its descendants remain widely used for embeddings and reranking because they are small and fast.

Exam tip

BERT is an encoder model for understanding and embeddings, not a chat or text-generation model.

Related terms