Σχετικά με το έγγραφο αυτό
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Vladimir Karpukhin
- sl:arxiv_num : 2004.04906
- sl:arxiv_published : 2020-04-10T04:53:17Z
- sl:arxiv_summary : 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%-19% absolute in terms of top-20 passage retrieval accuracy, and helps our
end-to-end QA system establish new state-of-the-art on multiple open-domain QA
benchmarks.@en
- sl:arxiv_title : Dense Passage Retrieval for Open-Domain Question Answering@en
- sl:arxiv_updated : 2020-09-30T21:27:13Z
- sl:bookmarkOf : https://arxiv.org/abs/2004.04906
- sl:creationDate : 2021-06-03
- sl:creationTime : 2021-06-03T11:06:07Z