Dense Passage Retrieval for Open-Domain Question Answering Article Swipe

PDF

Related Concepts

Question answering Computer science Open domain Information retrieval Vector space model Domain (mathematical analysis) Dual (grammatical number) De facto Encoder Simple (philosophy) Artificial intelligence Natural language processing Mathematics Operating system Political science Epistemology Literature Law Art Mathematical analysis Philosophy

Vladimir Karpukhin , Barlas Oğuz , Sewon Min , Patrick Lewis , Ledell Wu , Sergey Edunov , Danqi Chen , Wen-tau Yih ·

YOU? · · 2020 · Open Access · · DOI: https://doi.org/10.18653/v1/2020.emnlp-main.550 · OA: W3015883388

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.