Teknosys learning library

6. BERT, recurrent networks, and RNTN

BERT is a bidirectional transformer encoder, commonly adapted for classification, token labeling, and extractive question answering. RNNs process sequences with a recurrent hidden state; LSTMs and GRUs add memory gates.

Recursive neural tensor networks (RNTNs) compose representations along structures such as parse trees and have been used for phrase-level sentiment. The informal term “RNT” is ambiguous: recursive composition is different from recurrent processing and different again from transformer attention.

Educational material. Verify examples against current documentation and applicable licenses. Report a correction.