{"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/span-based-open-information-extraction","title":"Span Model for Open Information Extraction on Accurate Corpus","arxiv_id":"1901.10879","date":"2019-01-30","proceeding":null,"authors":["Junlang Zhan","Hai Zhao"],"abstract":"Open information extraction (Open IE) is a challenging task especially due to its brittle data basis. Most of Open IE systems have to be trained on automatically built corpus and evaluated on inaccurate test set. In this work, we first alleviate this difficulty from both sides of training and test sets. For the former, we propose an improved model design to more sufficiently exploit training dataset. For the latter, we present our accurately re-annotated benchmark test set (Re-OIE6) according to a series of linguistic observation and analysis. Then, we introduce a span model instead of previous adopted sequence labeling formulization for n-ary Open IE. Our newly introduced model achieves new state-of-the-art performance on both benchmark evaluation datasets.","url_abs":"https://arxiv.org/abs/1901.10879v6","url_pdf":"https://arxiv.org/pdf/1901.10879v6.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":"span-based-open-information-extraction","repo_url":"https://github.com/zhanjunlang/Span_OIE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"open-information-extraction","task_name":"Open Information Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-information-extraction-on-oie2016","task":"Open Information Extraction","dataset":"OIE2016","model":"SpanOIE","rank_in_archive_order":5,"of":12,"metrics":{"F1":"68.65"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.10879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10879"}},"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/zhanjunlang/Span_OIE","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"ran_fixture":2},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"a9ace46c90ab02c8","entry":"f_beta","repo":"zhanjunlang/Span_OIE","repo_kind":"official","path":"evaluate/evaluate.py","file_url":"https://github.com/zhanjunlang/Span_OIE/blob/HEAD/evaluate/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a9ace46c90ab02c8"}},{"code_sha256_prefix":"652e6ae7ede80cf4","entry":"lr_decay","repo":"zhanjunlang/Span_OIE","repo_kind":"official","path":"main_span.py","file_url":"https://github.com/zhanjunlang/Span_OIE/blob/HEAD/main_span.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"652e6ae7ede80cf4"}},{"code_sha256_prefix":"95607edc5b16ba37","entry":"span_candidates_filter","repo":"zhanjunlang/Span_OIE","repo_kind":"official","path":"main_span.py","file_url":"https://github.com/zhanjunlang/Span_OIE/blob/HEAD/main_span.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"95607edc5b16ba37"}},{"code_sha256_prefix":"804444d775fe7a34","entry":"syntax_check","repo":"zhanjunlang/Span_OIE","repo_kind":"official","path":"main_span.py","file_url":"https://github.com/zhanjunlang/Span_OIE/blob/HEAD/main_span.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"804444d775fe7a34"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}