Aller au contenu
Atlas de l'IA

Extraction d’information et NER

Extraire noms, lieux et relations d’un texte libre

Langage et connaissancesIntermédiaire #06
entréeTexteTexte

Le texte intégral est présenté en anglais ; le titre et le résumé sont localisés.

CE QUE DÉSIGNE CETTE CAPACITÉ

Takes natural-language text and returns structured fragments: typed entities (person, organisation, date, amount) plus the relations or events among them. Unlike classification it does not give one label to the whole text but locates spans; unlike schema-driven structured output, the extracted targets come from the text itself rather than a fully prescribed field list.

Comment c'est fait

Early systems used conditional random fields or rule-based sequence labelling, tagging tokens BIO-style; pre-trained encoders with a tagging head then became standard. Relation and event extraction are often framed as entity-pair classification or as generation of triples directly. More recently, large models perform few-shot or zero-shot extraction against a given schema, avoiding per-type annotation.

Produits représentatifs

5

Organisations concernées

Usages typiques

  • Clause and amount extraction from contracts and filings
  • Résumé parsing and talent-pool building
  • Drug and symptom recognition in clinical notes
  • News events and knowledge-graph construction

Comment on l'évalue

Span-level F1
A hit requires both boundary and type to be correct
Relation F1
Share of triples (head, relation, tail) matched exactly
Exact-match rate
Share of records whose fields are all correct

Limites et points difficiles

  • Nested and overlapping entities are flattened by token-level tagging schemes
  • Cross-sentence coreference is hard; pronouns bind to the wrong antecedent
  • Domain terms and novel words are missed when the type was unseen in training

Concepts sous-jacents