{"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/r3-reinforced-reader-ranker-for-open-domain","title":"R$^3$: Reinforced Reader-Ranker for Open-Domain Question Answering","arxiv_id":"1709.00023","date":"2017-08-31","proceeding":null,"authors":["Shuohang Wang","Mo Yu","Xiaoxiao Guo","Zhiguo Wang","Tim Klinger","Wei zhang","Shiyu Chang","Gerald Tesauro","Bo-Wen Zhou","Jing Jiang"],"abstract":"In recent years researchers have achieved considerable success applying\nneural network methods to question answering (QA). These approaches have\nachieved state of the art results in simplified closed-domain settings such as\nthe SQuAD (Rajpurkar et al., 2016) dataset, which provides a pre-selected\npassage, from which the answer to a given question may be extracted. More\nrecently, researchers have begun to tackle open-domain QA, in which the model\nis given a question and access to a large corpus (e.g., wikipedia) instead of a\npre-selected passage (Chen et al., 2017a). This setting is more complex as it\nrequires large-scale search for relevant passages by an information retrieval\ncomponent, combined with a reading comprehension model that \"reads\" the\npassages to generate an answer to the question. Performance in this setting\nlags considerably behind closed-domain performance. In this paper, we present a\nnovel open-domain QA system called Reinforced Ranker-Reader $(R^3)$, based on\ntwo algorithmic innovations. First, we propose a new pipeline for open-domain\nQA with a Ranker component, which learns to rank retrieved passages in terms of\nlikelihood of generating the ground-truth answer to a given question. Second,\nwe propose a novel method that jointly trains the Ranker along with an\nanswer-generation Reader model, based on reinforcement learning. We report\nextensive experimental results showing that our method significantly improves\non the state of the art for multiple open-domain QA datasets.","url_abs":"http://arxiv.org/abs/1709.00023v2","url_pdf":"http://arxiv.org/pdf/1709.00023v2.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":"r3-reinforced-reader-ranker-for-open-domain","repo_url":"https://github.com/shuohangwang/mprc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"answer-generation","task_name":"Answer Generation"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-domain-question-answering-on-quasar","task":"Open-Domain Question Answering","dataset":"Quasar","model":"R^3","rank_in_archive_order":4,"of":6,"metrics":{"EM (Quasar-T)":"35.3","F1 (Quasar-T)":"41.7"},"uses_additional_data":false},{"leaderboard":"/sota/open-domain-question-answering-on-searchqa","task":"Open-Domain Question Answering","dataset":"SearchQA","model":"R^3","rank_in_archive_order":8,"of":14,"metrics":{"EM":"49.0","F1":"55.3","N-gram F1":"-","Unigram Acc":"-"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.00023","atlas_url":"https://app.syntology.ai/?focus=1709.00023","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":"1709.00023"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1709.00023\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1709.00023"},"call":"get_concepts_for_paper(arxiv_id=\"1709.00023\")"}],"by_repo":[{"repo":"shuohangwang/mprc","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1711.05116"],"harvested_for_calls":[{"arxiv_id":"1711.05116","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1711.05116"},"call":"get_harvested_code_for_paper(arxiv_id=\"1711.05116\")"}]}],"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":"8cc39cf4c04a44b39134a218923b0f56a42f54c19caff455a0675cbd332e5765","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}