Dense Passage Retrieval for Open-Domain Question Answering

by   Vladimir Karpukhin, et al.

Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework. When evaluated on a wide range of open-domain QA datasets, our dense retriever outperforms a strong Lucene-BM25 system largely by 9 end-to-end QA system establish new state-of-the-art on multiple open-domain QA benchmarks.


page 1

page 2

page 3

page 4


Top K Relevant Passage Retrieval for Biomedical Question Answering

Question answering is a task that answers factoid questions using a larg...

Open Domain Question Answering over Tables via Dense Retrieval

Recent advances in open-domain QA have led to strong models based on den...

Dense Hierarchical Retrieval for Open-Domain Question Answering

Dense neural text retrieval has achieved promising results on open-domai...

SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval

We introduce SPARTA, a novel neural retrieval method that shows great pr...

Learning to Retrieve Passages without Supervision

Dense retrievers for open-domain question answering (ODQA) have been sho...

A Replication Study of Dense Passage Retriever

Text retrieval using learned dense representations has recently emerged ...

Relevance-guided Supervision for OpenQA with ColBERT

Systems for Open-Domain Question Answering (OpenQA) generally depend on ...

Please sign up or login with your details

Forgot password? Click here to reset