{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/salient-phrase-aware-dense-retrieval-can-a","title":"Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?","arxiv_id":"2110.06918","date":"2021-10-13","proceeding":null,"authors":["Xilun Chen","Kushal Lakhotia","Barlas Oğuz","Anchit Gupta","Patrick Lewis","Stan Peshterliev","Yashar Mehdad","Sonal Gupta","Wen-tau Yih"],"abstract":"Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain data. It has been argued that this is an inherent limitation of dense models. We rebut this claim by introducing the Salient Phrase Aware Retriever (SPAR), a dense retriever with the lexical matching capacity of a sparse model. We show that a dense Lexical Model {\\Lambda} can be trained to imitate a sparse one, and SPAR is built by augmenting a standard dense retriever with {\\Lambda}. Empirically, SPAR shows superior performance on a range of tasks including five question answering datasets, MS MARCO passage retrieval, as well as the EntityQuestions and BEIR benchmarks for out-of-domain evaluation, exceeding the performance of state-of-the-art dense and sparse retrievers. The code and models of SPAR are available at: https://github.com/facebookresearch/dpr-scale/tree/main/spar","url_abs":"https://arxiv.org/abs/2110.06918v3","url_pdf":"https://arxiv.org/pdf/2110.06918v3.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":"salient-phrase-aware-dense-retrieval-can-a","repo_url":"https://github.com/facebookresearch/dpr-scale","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"salient-phrase-aware-dense-retrieval-can-a","repo_url":"https://github.com/facebookresearch/dpr-scale/tree/main/spar","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"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":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/passage-retrieval-on-entityquestions","task":"Passage Retrieval","dataset":"EntityQuestions","model":"SPAR-PAQ","rank_in_archive_order":2,"of":7,"metrics":{"Recall@20":"0.740"},"uses_additional_data":false},{"leaderboard":"/sota/passage-retrieval-on-natural-questions","task":"Passage Retrieval","dataset":"Natural Questions","model":"SPAR","rank_in_archive_order":3,"of":10,"metrics":{"Precision@100":"88.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.06918","atlas_url":"https://app.syntology.ai/?focus=2110.06918","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2110.06918"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.06918\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.06918"},"call":"get_concepts_for_paper(arxiv_id=\"2110.06918\")"}],"by_repo":[{"repo":"facebookresearch/dpr-scale","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2502.18460"],"harvested_for_calls":[{"arxiv_id":"2502.18460","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.18460"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.18460\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a2502bbc985bcf1aaf9913c430f9d8187f1f2f79acf732408e2f0aa4db950e27","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}