Embeddings & Vector SearchRodrigo Nogueira, Kyunghyun Cho (NYU)Kyunghyun ChoNew York University (NYU)

Nogueira and Cho present Passage Re-ranking with BERT

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Presented Passage Re-ranking with BERT — cross-encoder re-ranking that takes a query-document pair as a single input

Why it matters

The prototype of the reranker lineage. Standardized the two-stage structure that recovers, at a later stage, the precision dense embeddings miss

Source — Primary sources first; secondary reports are labelled “Press”

Paperarxiv.orghttps://arxiv.org/abs/1901.04085

Added in Week 35, 2026 · See that week

On the map — ⑰ Embeddings line

  1. Previous stopFAISS
  2. This recordNogueira and Cho present Passage Re-ranking with BERT
  3. Next stopSentence-BERT
See it on the map

Nearby on the same axis

Reimers and Gurevych present Sentence-BERTPaperMicrosoft Research India and CMU present DiskANNPaperShen et al. present Towards Backward-Compatible Representation LearningPaperKarpukhin et al. present Dense Passage RetrievalPaper