Dense Passage Retrieval for Open-Domain Question Answering
| Autor: | Sergey Edunov, Wen-tau Yih, Danqi Chen, Vladimir Karpukhin, Sewon Min, Barlas Oguz, Patrick S. H. Lewis, Ledell Wu |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Information retrieval Computer Science - Computation and Language Computer science InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL 02 engineering and technology Space (commercial competition) 03 medical and health sciences Range (mathematics) 0302 clinical medicine Simple (abstract algebra) 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering Open domain Question answering 020201 artificial intelligence & image processing Computation and Language (cs.CL) |
| Zdroj: | EMNLP (1) |
| DOI: | 10.48550/arxiv.2004.04906 |
| Popis: | 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. Comment: EMNLP 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|