%0 Generic %1 karpukhin2020dense %A Karpukhin, Vladimir %A Oğuz, Barlas %A Min, Sewon %A Lewis, Patrick %A Wu, Ledell %A Edunov, Sergey %A Chen, Danqi %A Yih, Wen-tau %D 2020 %K masterthesis passage-retrieval qna %T Dense Passage Retrieval for Open-Domain Question Answering %U http://arxiv.org/abs/2004.04906 %X 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.

@misc{karpukhin2020dense, abstract = {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.}, added-at = {2021-01-05T08:24:04.000+0100}, author = {Karpukhin, Vladimir and Oğuz, Barlas and Min, Sewon and Lewis, Patrick and Wu, Ledell and Edunov, Sergey and Chen, Danqi and Yih, Wen-tau}, biburl = {https://www.bibsonomy.org/bibtex/261eba91471f2061ad1498326279074fa/festplatte}, description = {[2004.04906] Dense Passage Retrieval for Open-Domain Question Answering}, interhash = {8bc2fecf271bbd4e3fa16fcafc2f8da9}, intrahash = {61eba91471f2061ad1498326279074fa}, keywords = {masterthesis passage-retrieval qna}, note = {cite arxiv:2004.04906Comment: EMNLP 2020}, timestamp = {2021-01-07T16:13:41.000+0100}, title = {Dense Passage Retrieval for Open-Domain Question Answering}, url = {http://arxiv.org/abs/2004.04906}, year = 2020 }