{"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/repbert-contextualized-text-embeddings-for","title":"RepBERT: Contextualized Text Embeddings for First-Stage Retrieval","arxiv_id":"2006.15498","date":"2020-06-28","proceeding":null,"authors":["Jingtao Zhan","Jiaxin Mao","Yiqun Liu","Min Zhang","Shaoping Ma"],"abstract":"Although exact term match between queries and documents is the dominant method to perform first-stage retrieval, we propose a different approach, called RepBERT, to represent documents and queries with fixed-length contextualized embeddings. The inner products of query and document embeddings are regarded as relevance scores. On MS MARCO Passage Ranking task, RepBERT achieves state-of-the-art results among all initial retrieval techniques. And its efficiency is comparable to bag-of-words methods.","url_abs":"https://arxiv.org/abs/2006.15498v2","url_pdf":"https://arxiv.org/pdf/2006.15498v2.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":"repbert-contextualized-text-embeddings-for","repo_url":"https://github.com/jingtaozhan/RepBERT-Index","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"repbert-contextualized-text-embeddings-for","repo_url":"https://github.com/jingtaozhan/JPQ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"repbert-contextualized-text-embeddings-for","repo_url":"https://github.com/jingtaozhan/repconc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"passage-ranking","task_name":"Passage Ranking"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.15498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.15498"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jingtaozhan/JPQ","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jingtaozhan/repconc","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jingtaozhan/RepBERT-Index","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"260e8196afc0aba3","entry":"create_embed_memmap","repo":"jingtaozhan/RepBERT-Index","repo_kind":"official","path":"precompute.py","file_url":"https://github.com/jingtaozhan/RepBERT-Index/blob/HEAD/precompute.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"260e8196afc0aba3"}},{"code_sha256_prefix":"41ba77b6bc6bb61e","entry":"raise_immediately","repo":"jingtaozhan/RepBERT-Index","repo_kind":"official","path":"multi_retrieve.py","file_url":"https://github.com/jingtaozhan/RepBERT-Index/blob/HEAD/multi_retrieve.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"41ba77b6bc6bb61e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}