Aller au contenu
Atlas de l'IA

Plongements de texte et recherche sémantique

Transformer les phrases en vecteurs et récupérer les plus proches par sens

Langage et connaissancesIntermédiaire #09
entréeTexteTableau

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

CE QUE DÉSIGNE CETTE CAPACITÉ

Encodes a piece of text into a fixed-length vector so that semantically similar texts sit close together, then retrieves related items by nearest-neighbour lookup. Output is a ranked result list (item ids and scores), not prose. Unlike question answering it only finds possibly relevant material; it does not compose the answer.

Comment c'est fait

The mainstream design is a two-tower model: queries and documents are compressed by encoders, and training pushes true pairs above random negatives, typically with contrastive learning and large batches. At query time all document vectors are pre-computed into an index and an approximate nearest-neighbour search returns the top-k in milliseconds. Sparse and dense representations are often mixed to combine keyword hits with semantic recall.

Produits représentatifs

6

Organisations concernées

Usages typiques

  • Search over enterprise documents and code
  • The recall stage of RAG pipelines
  • Deduplication, clustering and topic discovery
  • Recommendation and similar-content entry points

Comment on l'évalue

Recall@k
Whether the top-k contain all relevant documents
nDCG
Discounted cumulative gain that accounts for rank position
MRR
Mean reciprocal rank of the first relevant result

Limites et points difficiles

  • Semantic similarity is not relevance: near neighbours may merely share wording
  • Cross-domain or cross-lingual use degrades noticeably without adaptation
  • Chunking long documents severs context, and answers at chunk boundaries are easily missed

Concepts sous-jacents