{"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/end-to-end-open-domain-question-answering","title":"End-to-End Open-Domain Question Answering with BERTserini","arxiv_id":"1902.01718","date":"2019-02-05","proceeding":"NAACL 2019 6","authors":["Wei Yang","Yuqing Xie","Aileen Lin","Xingyu Li","Luchen Tan","Kun Xiong","Ming Li","Jimmy Lin"],"abstract":"We demonstrate an end-to-end question answering system that integrates BERT with the open-source Anserini information retrieval toolkit. In contrast to most question answering and reading comprehension models today, which operate over small amounts of input text, our system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles in an end-to-end fashion. We report large improvements over previous results on a standard benchmark test collection, showing that fine-tuning pretrained BERT with SQuAD is sufficient to achieve high accuracy in identifying answer spans.","url_abs":"https://arxiv.org/abs/1902.01718v2","url_pdf":"https://arxiv.org/pdf/1902.01718v2.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":"end-to-end-open-domain-question-answering","repo_url":"https://github.com/rsvp-ai/bertserini","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"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":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-domain-question-answering-on-squad1-1","task":"Open-Domain Question Answering","dataset":"SQuAD1.1 dev","model":"BERTserini","rank_in_archive_order":4,"of":4,"metrics":{"EM":"38.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.01718","atlas_url":"https://app.syntology.ai/?focus=1902.01718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01718"}},"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/rsvp-ai/bertserini","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":8,"ran":4,"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":"9df40357afea56cc","entry":"to_list","repo":"rsvp-ai/bertserini","repo_kind":"official","path":"bertserini/train/run_squad.py","file_url":"https://github.com/rsvp-ai/bertserini/blob/HEAD/bertserini/train/run_squad.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9df40357afea56cc"}},{"code_sha256_prefix":"9026d9da5d085bd4","entry":"compute_exact","repo":"rsvp-ai/bertserini","repo_kind":"official","path":"bertserini/utils/utils_squad_metrics.py","file_url":"https://github.com/rsvp-ai/bertserini/blob/HEAD/bertserini/utils/utils_squad_metrics.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9026d9da5d085bd4"}},{"code_sha256_prefix":"aa6bc32d9c17a2f1","entry":"get_tokens","repo":"rsvp-ai/bertserini","repo_kind":"official","path":"bertserini/utils/utils_squad_metrics.py","file_url":"https://github.com/rsvp-ai/bertserini/blob/HEAD/bertserini/utils/utils_squad_metrics.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa6bc32d9c17a2f1"}},{"code_sha256_prefix":"6a96435eba311b08","entry":"normalize_answer","repo":"rsvp-ai/bertserini","repo_kind":"official","path":"bertserini/utils/utils_squad_metrics.py","file_url":"https://github.com/rsvp-ai/bertserini/blob/HEAD/bertserini/utils/utils_squad_metrics.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a96435eba311b08"}},{"code_sha256_prefix":"20bfdca6b0a6c2a7","entry":"choose_best_answer","repo":"rsvp-ai/bertserini","repo_kind":"official","path":"bertserini/utils/utils.py","file_url":"https://github.com/rsvp-ai/bertserini/blob/HEAD/bertserini/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20bfdca6b0a6c2a7"}},{"code_sha256_prefix":"4dcd04d7f6a7d02a","entry":"get_best_answer","repo":"rsvp-ai/bertserini","repo_kind":"official","path":"bertserini/utils/utils_new.py","file_url":"https://github.com/rsvp-ai/bertserini/blob/HEAD/bertserini/utils/utils_new.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4dcd04d7f6a7d02a"}},{"code_sha256_prefix":"b668a6a9dda0f7b1","entry":"strip_accents","repo":"rsvp-ai/bertserini","repo_kind":"official","path":"bertserini/utils/utils.py","file_url":"https://github.com/rsvp-ai/bertserini/blob/HEAD/bertserini/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b668a6a9dda0f7b1"}},{"code_sha256_prefix":"167ccd707d8de0a4","entry":"weighted_score","repo":"rsvp-ai/bertserini","repo_kind":"official","path":"bertserini/utils/utils.py","file_url":"https://github.com/rsvp-ai/bertserini/blob/HEAD/bertserini/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"167ccd707d8de0a4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}