AI engineering glossary · NLP embeddings
What is Bidirectional LSTM-CRF?
Bidirectional LSTM-CRF (also called BiLSTM-CRF): A sequence-labelling architecture combining a bidirectional LSTM, which reads text left-to-right and right-to-left to build a vector for each token, with a CRF layer that picks the best overall label sequence. It was a standard high-performing design for entity recognition before transformers.
Bidirectional LSTM-CRF: an example
A BiLSTM-CRF tagger reads "Rahul joined Wipro" and outputs B-PER O B-ORG.
Related terms
More NLP embeddings terms
- Bigram
- BILOU tagging
- BIO tagging
- BM25
- Byte-level BPE
- Byte-pair encoding
- Case folding
- Character-level tokenisation
Where you learn it
Bidirectional LSTM-CRF is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.