Dense Passage Retrieval for Open-Domain Question Answering¶
Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., et al. (2020). Dense Passage Retrieval for Open-Domain Question Answering. Proceedings of EMNLP 2020, 6769-6781.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Encoding Specificity
- In information retrieval, a document indexed with one embedding model is retrievable only by queries embedded in the same space, and switching the query encoder while leaving the index unchanged silently breaks retrieval — the content is there, but the key has changed.
This sourceDual-encoder dense retrieval: documents are indexed as embeddings from a passage encoder and queries embedded by a separate encoder into the same space, with retrieval by dot-product/cosine similarity — supporting that the encoder's learned space is the storage key, that similarity is the match function, and that a query encoder mismatched to the index space breaks retrieval (requiring re-embedding or jointly trained encoders).
- In information retrieval, a document indexed with one embedding model is retrievable only by queries embedded in the same space, and switching the query encoder while leaving the index unchanged silently breaks retrieval — the content is there, but the key has changed.
Verification¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Registry ID ref:85a5c21c9c32 · see in the full table