AI glossary Models & Architecture
What is BERT?
BERT (Bidirectional Encoder Representations from Transformers)
← All glossary terms In short
Pre-trained language model that revolutionized NLP; foundation of many semantic search systems.
Explained
BERT is a Transformer-based model pre-trained on large text corpora. It learns bidirectional context and is used for tasks like semantic search, question answering, and classification. It paved the way for modern LLMs.
Where it shows up at Thinkia
Products
The Mesh