Publication

Dense Passage Retrieval for Open-Domain Question Answering

Conference on Empirical Methods in Natural Language Processing (EMNLP)


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 greatly 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.

Related Publications

All Publications

EACL - April 22, 2021

WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia

Holger Schwenk, Vishrav Chaudhary, Shuo Sun, Hongyu Gong, Francisco Guzmán

ICLR - April 29, 2021

Autoregressive Entity Retrieval

Nicola De Cao, Gautier Izacard, Sebastian Riedel, Fabio Petroni

ICLR - May 3, 2021

Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval

Wenhan Xiong, Xiang Lorraine Li, Srinivasan Iyer, Jingfei Du, Patrick Lewis, William Wang, Yashar Mehdad, Wen-tau Yih, Sebastian Riedel, Douwe Kiela, Barlas Oğuz

ICASSP - June 6, 2021

Multi-Channel Speech Enhancement Using Graph Neural Networks

Panagiotis Tzirakis, Anurag Kumar, Jacob Donley

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy