{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/efficient-passage-retrieval-with-hashing-for","title":"Efficient Passage Retrieval with Hashing for Open-domain Question Answering","arxiv_id":"2106.00882","date":"2021-06-02","proceeding":"ACL 2021 5","authors":["Ikuya Yamada","Akari Asai","Hannaneh Hajishirzi"],"abstract":"Most state-of-the-art open-domain question answering systems use a neural retrieval model to encode passages into continuous vectors and extract them from a knowledge source. However, such retrieval models often require large memory to run because of the massive size of their passage index. In this paper, we introduce Binary Passage Retriever (BPR), a memory-efficient neural retrieval model that integrates a learning-to-hash technique into the state-of-the-art Dense Passage Retriever (DPR) to represent the passage index using compact binary codes rather than continuous vectors. BPR is trained with a multi-task objective over two tasks: efficient candidate generation based on binary codes and accurate reranking based on continuous vectors. Compared with DPR, BPR substantially reduces the memory cost from 65GB to 2GB without a loss of accuracy on two standard open-domain question answering benchmarks: Natural Questions and TriviaQA. Our code and trained models are available at https://github.com/studio-ousia/bpr.","url_abs":"https://arxiv.org/abs/2106.00882v1","url_pdf":"https://arxiv.org/pdf/2106.00882v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"efficient-passage-retrieval-with-hashing-for","repo_url":"https://github.com/studio-ousia/bpr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"natural-questions","task_name":"Natural Questions"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"passage-retrieval","task_name":"Passage Retrieval"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reranking","task_name":"Reranking"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"triviaqa","task_name":"TriviaQA"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-domain-question-answering-on-natural","task":"Open-Domain Question Answering","dataset":"Natural Questions","model":"BPR (linear scan; l=1000)","rank_in_archive_order":5,"of":5,"metrics":{"Exact Match":"41.6"},"uses_additional_data":false},{"leaderboard":"/sota/open-domain-question-answering-on-tqa","task":"Open-Domain Question Answering","dataset":"TQA","model":"BPR (linear scan; l=1000)","rank_in_archive_order":2,"of":2,"metrics":{"Exact Match":"56.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-natural-questions-long","task":"Question Answering","dataset":"Natural Questions (long)","model":"BPR (linear scan; l=1000)","rank_in_archive_order":13,"of":13,"metrics":{"EM":"41.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.00882","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}