AI engineering glossary · NLP embeddings
What is relation extraction?
Relation extraction: Finding and labelling relationships between entities in text, producing facts such as (person, works_at, company). It commonly follows named entity recognition and feeds knowledge graphs, which store such facts as connected records.
Relation extraction: an example
From "Sundar Pichai leads Google", it extracts the triple (Sundar Pichai, CEO_of, Google).
Related terms
More NLP embeddings terms
- Semantic role labelling
- Semantic similarity
- Semantic textual similarity
- Sentence embedding
- Sentence segmentation
- Sentence-BERT
- SentencePiece
- Sentiment analysis
Where you learn it
Relation extraction is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.