{"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/globally-normalized-reader","title":"Globally Normalized Reader","arxiv_id":"1709.02828","date":"2017-09-08","proceeding":"EMNLP 2017 9","authors":["Jonathan Raiman","John Miller"],"abstract":"Rapid progress has been made towards question answering (QA) systems that can\nextract answers from text. Existing neural approaches make use of expensive\nbi-directional attention mechanisms or score all possible answer spans,\nlimiting scalability. We propose instead to cast extractive QA as an iterative\nsearch problem: select the answer's sentence, start word, and end word. This\nrepresentation reduces the space of each search step and allows computation to\nbe conditionally allocated to promising search paths. We show that globally\nnormalizing the decision process and back-propagating through beam search makes\nthis representation viable and learning efficient. We empirically demonstrate\nthe benefits of this approach using our model, Globally Normalized Reader\n(GNR), which achieves the second highest single model performance on the\nStanford Question Answering Dataset (68.4 EM, 76.21 F1 dev) and is 24.7x faster\nthan bi-attention-flow. We also introduce a data-augmentation method to produce\nsemantically valid examples by aligning named entities to a knowledge base and\nswapping them with new entities of the same type. This method improves the\nperformance of all models considered in this work and is of independent\ninterest for a variety of NLP tasks.","url_abs":"http://arxiv.org/abs/1709.02828v1","url_pdf":"http://arxiv.org/pdf/1709.02828v1.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":"globally-normalized-reader","repo_url":"https://github.com/baidu-research/GloballyNormalizedReader","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.02828","atlas_url":"https://app.syntology.ai/?focus=1709.02828","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":"1709.02828"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1709.02828\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1709.02828"},"call":"get_concepts_for_paper(arxiv_id=\"1709.02828\")"}],"by_repo":[{"repo":"baidu-research/GloballyNormalizedReader","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"46d1d0882ebca5f4ff9c218bf4ed84e3be286a4b3910b1cd0c29debe1d5c2c61","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}