Dense Passage Retrieval for Open-Domain Question Answering

Why this idea matters

Retrieval quality can be studied separately from the answering model.

The proposal

DPR examines whether learned dense representations can provide practical passage retrieval for open-domain QA, using a comparatively simple dual-encoder framework.

What was inspected

Its abstract reports stronger retrieval than a Lucene BM25 baseline on evaluated datasets. That is an author-reported comparison, not a claim that every dense index beats lexical search.

Editorial interpretation

Before evaluating an answer, inspect whether the needed passage entered the candidate set. Retrieval errors and generation errors call for different interventions.

The mechanism, in brief

1. Encode questions and passages.
2. Search the shared representation space.
3. Pass candidate contexts to a QA system.

Limits of this note

• Dense retrieval superiority is not universal.
• Dataset and negative-sampling details remain unreviewed here.

Continue reading

To examine another paper and keep working notes, open the Paper desk. Those notes stay in your browser until you export them.