{"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/reading-wikipedia-to-answer-open-domain","title":"Reading Wikipedia to Answer Open-Domain Questions","arxiv_id":"1704.00051","date":"2017-03-31","proceeding":"ACL 2017 7","authors":["Danqi Chen","Adam Fisch","Jason Weston","Antoine Bordes"],"abstract":"This paper proposes to tackle open- domain question answering using Wikipedia\nas the unique knowledge source: the answer to any factoid question is a text\nspan in a Wikipedia article. This task of machine reading at scale combines the\nchallenges of document retrieval (finding the relevant articles) with that of\nmachine comprehension of text (identifying the answer spans from those\narticles). Our approach combines a search component based on bigram hashing and\nTF-IDF matching with a multi-layer recurrent neural network model trained to\ndetect answers in Wikipedia paragraphs. Our experiments on multiple existing QA\ndatasets indicate that (1) both modules are highly competitive with respect to\nexisting counterparts and (2) multitask learning using distant supervision on\ntheir combination is an effective complete system on this challenging task.","url_abs":"http://arxiv.org/abs/1704.00051v2","url_pdf":"http://arxiv.org/pdf/1704.00051v2.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":"reading-wikipedia-to-answer-open-domain","repo_url":"https://github.com/facebookresearch/DrQA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"reading-wikipedia-to-answer-open-domain","repo_url":"https://github.com/BAJUKA/SQuAD-NLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"reading-wikipedia-to-answer-open-domain","repo_url":"https://github.com/HKUST-KnowComp/MnemonicReader","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"reading-wikipedia-to-answer-open-domain","repo_url":"https://github.com/Raman-Raje/Machine-Reading-Comprehension-Neural-Question-Answer-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"reading-wikipedia-to-answer-open-domain","repo_url":"https://github.com/aaronbae/AnaQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"reading-wikipedia-to-answer-open-domain","repo_url":"https://github.com/facebookresearch/ParlAI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"reading-wikipedia-to-answer-open-domain","repo_url":"https://github.com/iCompass-ai/TunBERT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"reading-wikipedia-to-answer-open-domain","repo_url":"https://github.com/sachit-n/drqa_doc_reader","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"reading-wikipedia-to-answer-open-domain","repo_url":"https://github.com/xiangyue9607/CliniRC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"reading-wikipedia-to-answer-open-domain","repo_url":"https://github.com/hitvoice/DrQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"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":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-domain-question-answering-on-squad11","task":"Open-Domain Question Answering","dataset":"SQuAD1.1","model":"DrQA","rank_in_archive_order":1,"of":3,"metrics":{"EM":"70.0"},"uses_additional_data":false},{"leaderboard":"/sota/open-domain-question-answering-on-searchqa","task":"Open-Domain Question Answering","dataset":"SearchQA","model":"DrQA","rank_in_archive_order":9,"of":14,"metrics":{"EM":"41.9"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-natural-questions-long","task":"Question Answering","dataset":"Natural Questions (long)","model":"DrQA","rank_in_archive_order":8,"of":13,"metrics":{"F1":"46.1"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-quasart-t","task":"Question Answering","dataset":"Quasart-T","model":"DrQA","rank_in_archive_order":7,"of":7,"metrics":{"EM":"37.7"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"Document Reader (single model)","rank_in_archive_order":158,"of":213,"metrics":{"EM":"70.733","F1":"79.353"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset":"SQuAD1.1 dev","model":"DrQA (Document Reader only)","rank_in_archive_order":38,"of":55,"metrics":{"EM":"69.5","F1":"78.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.00051","atlas_url":"https://app.syntology.ai/?focus=1704.00051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.00051"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/facebookresearch/ParlAI","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hitvoice/DrQA","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Raman-Raje/Machine-Reading-Comprehension-Neural-Question-Answer-","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BAJUKA/SQuAD-NLP","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iCompass-ai/TunBERT","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HKUST-KnowComp/MnemonicReader","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiangyue9607/CliniRC","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/DrQA","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sachit-n/drqa_doc_reader","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aaronbae/AnaQA","reach":{"status":"ok"}}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"49a768f04aa6cc7c","entry":"get_uncased_match","repo":"sachit-n/drqa_doc_reader","repo_kind":"listed","path":"model.py","file_url":"https://github.com/sachit-n/drqa_doc_reader/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"49a768f04aa6cc7c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}