{"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/a-bert-baseline-for-the-natural-questions","title":"A BERT Baseline for the Natural Questions","arxiv_id":"1901.08634","date":"2019-01-24","proceeding":null,"authors":["Chris Alberti","Kenton Lee","Michael Collins"],"abstract":"This technical note describes a new baseline for the Natural Questions. Our model is based on BERT and reduces the gap between the model F1 scores reported in the original dataset paper and the human upper bound by 30% and 50% relative for the long and short answer tasks respectively. This baseline has been submitted to the official NQ leaderboard at ai.google.com/research/NaturalQuestions. Code, preprocessed data and pretrained model are available at https://github.com/google-research/language/tree/master/language/question_answering/bert_joint.","url_abs":"https://arxiv.org/abs/1901.08634v3","url_pdf":"https://arxiv.org/pdf/1901.08634v3.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":"a-bert-baseline-for-the-natural-questions","repo_url":"https://github.com/google-research/language","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"a-bert-baseline-for-the-natural-questions","repo_url":"https://github.com/gooofy/zbrain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"a-bert-baseline-for-the-natural-questions","repo_url":"https://github.com/see--/natural-question-answering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"natural-questions","task_name":"Natural Questions"},{"task_slug":"question-answering","task_name":"Question Answering"}],"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/question-answering-on-natural-questions-long","task":"Question Answering","dataset":"Natural Questions (long)","model":"BERTjoint","rank_in_archive_order":6,"of":13,"metrics":{"F1":"64.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.08634","atlas_url":"https://app.syntology.ai/?focus=1901.08634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08634"}},"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/gooofy/zbrain","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/see--/natural-question-answering","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/language","reach":null}],"summary":{"ran":8,"unverified":2},"by_repo_kind":{"listed":{"samples":10,"ran":8,"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":"3c6f00ab6a9f35b3","entry":"convert_to_functional_api","repo":"see--/natural-question-answering","repo_kind":"listed","path":"export_tfhub.py","file_url":"https://github.com/see--/natural-question-answering/blob/HEAD/export_tfhub.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c6f00ab6a9f35b3"}},{"code_sha256_prefix":"28da9238ac641da4","entry":"enumerate_tags","repo":"see--/natural-question-answering","repo_kind":"listed","path":"nq_to_squad.py","file_url":"https://github.com/see--/natural-question-answering/blob/HEAD/nq_to_squad.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"28da9238ac641da4"}},{"code_sha256_prefix":"3c9035c96be8a79b","entry":"find_closing_tag","repo":"see--/natural-question-answering","repo_kind":"listed","path":"utils_nq.py","file_url":"https://github.com/see--/natural-question-answering/blob/HEAD/utils_nq.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c9035c96be8a79b"}},{"code_sha256_prefix":"62b21856204f94f1","entry":"get_add_tokens","repo":"see--/natural-question-answering","repo_kind":"listed","path":"utils_nq.py","file_url":"https://github.com/see--/natural-question-answering/blob/HEAD/utils_nq.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"62b21856204f94f1"}},{"code_sha256_prefix":"47a5135d3347930d","entry":"get_f1","repo":"see--/natural-question-answering","repo_kind":"listed","path":"eval_server.py","file_url":"https://github.com/see--/natural-question-answering/blob/HEAD/eval_server.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47a5135d3347930d"}},{"code_sha256_prefix":"c1853b4dcdc05921","entry":"in_shorts","repo":"see--/natural-question-answering","repo_kind":"listed","path":"eval_server.py","file_url":"https://github.com/see--/natural-question-answering/blob/HEAD/eval_server.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1853b4dcdc05921"}},{"code_sha256_prefix":"b29ee0435be8282b","entry":"read_candidates","repo":"see--/natural-question-answering","repo_kind":"listed","path":"utils_nq.py","file_url":"https://github.com/see--/natural-question-answering/blob/HEAD/utils_nq.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b29ee0435be8282b"}},{"code_sha256_prefix":"3c42ee2b19a937f1","entry":"reshape_df","repo":"see--/natural-question-answering","repo_kind":"listed","path":"eval_server.py","file_url":"https://github.com/see--/natural-question-answering/blob/HEAD/eval_server.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c42ee2b19a937f1"}},{"code_sha256_prefix":"f9ad382c926b25b3","entry":"convert_nq_to_squad","repo":"see--/natural-question-answering","repo_kind":"listed","path":"nq_to_squad.py","file_url":"https://github.com/see--/natural-question-answering/blob/HEAD/nq_to_squad.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9ad382c926b25b3"}},{"code_sha256_prefix":"21a37595f49175a0","entry":"create_optimizer","repo":"see--/natural-question-answering","repo_kind":"listed","path":"optimization.py","file_url":"https://github.com/see--/natural-question-answering/blob/HEAD/optimization.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21a37595f49175a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}