Log In Sign Up

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


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...

Analysing Dense Passage Retrieval for Multi-hop Question Answering

We analyse the performance of passage retrieval models in the presence o...

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

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

ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval

Neural retrievers based on pre-trained language models (PLMs), such as d...

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 ...