{"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/an-empirical-study-of-incorporating-pseudo","title":"An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction","arxiv_id":"1909.00502","date":"2019-09-02","proceeding":"IJCNLP 2019 11","authors":["Shun Kiyono","Jun Suzuki","Masato Mita","Tomoya Mizumoto","Kentaro Inui"],"abstract":"The incorporation of pseudo data in the training of grammatical error correction models has been one of the main factors in improving the performance of such models. However, consensus is lacking on experimental configurations, namely, choosing how the pseudo data should be generated or used. In this study, these choices are investigated through extensive experiments, and state-of-the-art performance is achieved on the CoNLL-2014 test set ($F_{0.5}=65.0$) and the official test set of the BEA-2019 shared task ($F_{0.5}=70.2$) without making any modifications to the model architecture.","url_abs":"https://arxiv.org/abs/1909.00502v1","url_pdf":"https://arxiv.org/pdf/1909.00502v1.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":"an-empirical-study-of-incorporating-pseudo","repo_url":"https://github.com/butsugiri/gec-pseudodata","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"grammatical-error-correction","task_name":"Grammatical Error Correction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/grammatical-error-correction-on-bea-2019-test","task":"Grammatical Error Correction","dataset":"BEA-2019 (test)","model":"Transformer + Pre-train with Pseudo Data","rank_in_archive_order":14,"of":19,"metrics":{"F0.5":"70.2"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-correction-on-conll-2014","task":"Grammatical Error Correction","dataset":"CoNLL-2014 Shared Task","model":"Transformer + Pre-train with Pseudo Data","rank_in_archive_order":14,"of":23,"metrics":{"F0.5":"65.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1909.00502","atlas_url":"https://app.syntology.ai/?focus=1909.00502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.00502"}},"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/butsugiri/gec-pseudodata","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"097360b83adf4254","entry":"get_pair_statistics","repo":"butsugiri/gec-pseudodata","repo_kind":"official","path":"generate_pseudo_samples.py","file_url":"https://github.com/butsugiri/gec-pseudodata/blob/HEAD/generate_pseudo_samples.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"097360b83adf4254"}},{"code_sha256_prefix":"8644011efb17c983","entry":"get_vocabulary","repo":"butsugiri/gec-pseudodata","repo_kind":"official","path":"generate_pseudo_samples.py","file_url":"https://github.com/butsugiri/gec-pseudodata/blob/HEAD/generate_pseudo_samples.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8644011efb17c983"}},{"code_sha256_prefix":"1829a82a6193de49","entry":"replace_pair","repo":"butsugiri/gec-pseudodata","repo_kind":"official","path":"generate_pseudo_samples.py","file_url":"https://github.com/butsugiri/gec-pseudodata/blob/HEAD/generate_pseudo_samples.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1829a82a6193de49"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}