{"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/simple-and-effective-multi-paragraph-reading","title":"Simple and Effective Multi-Paragraph Reading Comprehension","arxiv_id":"1710.10723","date":"2017-10-29","proceeding":"ACL 2018 7","authors":["Christopher Clark","Matt Gardner"],"abstract":"We consider the problem of adapting neural paragraph-level question answering\nmodels to the case where entire documents are given as input. Our proposed\nsolution trains models to produce well calibrated confidence scores for their\nresults on individual paragraphs. We sample multiple paragraphs from the\ndocuments during training, and use a shared-normalization training objective\nthat encourages the model to produce globally correct output. We combine this\nmethod with a state-of-the-art pipeline for training models on document QA\ndata. Experiments demonstrate strong performance on several document QA\ndatasets. Overall, we are able to achieve a score of 71.3 F1 on the web portion\nof TriviaQA, a large improvement from the 56.7 F1 of the previous best system.","url_abs":"http://arxiv.org/abs/1710.10723v2","url_pdf":"http://arxiv.org/pdf/1710.10723v2.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":"simple-and-effective-multi-paragraph-reading","repo_url":"https://github.com/allenai/document-qa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"triviaqa","task_name":"TriviaQA"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"BiDAF + Self Attention (single model)","rank_in_archive_order":144,"of":213,"metrics":{"EM":"72.139","F1":"81.048"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-triviaqa","task":"Question Answering","dataset":"TriviaQA","model":"S-Norm","rank_in_archive_order":37,"of":56,"metrics":{"EM":"66.37","F1":"71.32"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1710.10723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10723"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/allenai/document-qa","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"c8554a5f8637091a","entry":"config_to_json","repo":"allenai/document-qa","repo_kind":"official","path":"docqa/configurable.py","file_url":"https://github.com/allenai/document-qa/blob/HEAD/docqa/configurable.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":"c8554a5f8637091a"}},{"code_sha256_prefix":"0a371114688eec02","entry":"describe","repo":"allenai/document-qa","repo_kind":"official","path":"docqa/configurable.py","file_url":"https://github.com/allenai/document-qa/blob/HEAD/docqa/configurable.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":"0a371114688eec02"}},{"code_sha256_prefix":"763e8d8ebb18501b","entry":"extract_tokens","repo":"allenai/document-qa","repo_kind":"official","path":"docqa/data_processing/document_splitter.py","file_url":"https://github.com/allenai/document-qa/blob/HEAD/docqa/data_processing/document_splitter.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":"763e8d8ebb18501b"}},{"code_sha256_prefix":"06cf9af35b53a1a5","entry":"shuffle_list_buckets","repo":"allenai/document-qa","repo_kind":"official","path":"docqa/dataset.py","file_url":"https://github.com/allenai/document-qa/blob/HEAD/docqa/dataset.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":"06cf9af35b53a1a5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}