Saltar al contenido
Atlas de IA

Embeddings de texto y búsqueda semántica

Convertir frases en vectores y buscar los más cercanos por significado

Lenguaje y conocimientoIntermedio #09
entradaTextoTabla

El texto completo se presenta en inglés; el título y el resumen están traducidos.

QUÉ SIGNIFICA ESTA CAPACIDAD

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.

Cómo se consigue técnicamente

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.

Productos representativos

6

Organizaciones relacionadas

Usos típicos

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

Cómo se evalúa

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

Límites y dificultades

  • 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

Conceptos detrás