{"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/gector-grammatical-error-correction-tag-not","title":"GECToR -- Grammatical Error Correction: Tag, Not Rewrite","arxiv_id":"2005.12592","date":"2020-05-26","proceeding":"WS 2020 7","authors":["Kostiantyn Omelianchuk","Vitaliy Atrasevych","Artem Chernodub","Oleksandr Skurzhanskyi"],"abstract":"In this paper, we present a simple and efficient GEC sequence tagger using a Transformer encoder. Our system is pre-trained on synthetic data and then fine-tuned in two stages: first on errorful corpora, and second on a combination of errorful and error-free parallel corpora. We design custom token-level transformations to map input tokens to target corrections. Our best single-model/ensemble GEC tagger achieves an $F_{0.5}$ of 65.3/66.5 on CoNLL-2014 (test) and $F_{0.5}$ of 72.4/73.6 on BEA-2019 (test). Its inference speed is up to 10 times as fast as a Transformer-based seq2seq GEC system. The code and trained models are publicly available.","url_abs":"https://arxiv.org/abs/2005.12592v2","url_pdf":"https://arxiv.org/pdf/2005.12592v2.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":"gector-grammatical-error-correction-tag-not","repo_url":"https://github.com/grammarly/gector","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"gector-grammatical-error-correction-tag-not","repo_url":"https://github.com/psawa/gecko-app","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"gector-grammatical-error-correction-tag-not","repo_url":"https://github.com/gotutiyan/gector","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"grammatical-error-correction","task_name":"Grammatical Error Correction"},{"task_slug":"tag","task_name":"TAG"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/grammatical-error-correction-on-bea-2019-test","task":"Grammatical Error Correction","dataset":"BEA-2019 (test)","model":"Sequence tagging + token-level transformations + two-stage fine-tuning (+RoBERTa, XLNet)","rank_in_archive_order":9,"of":19,"metrics":{"F0.5":"73.7"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-correction-on-bea-2019-test","task":"Grammatical Error Correction","dataset":"BEA-2019 (test)","model":"Sequence tagging + token-level transformations + two-stage fine-tuning (+XLNet)","rank_in_archive_order":13,"of":19,"metrics":{"F0.5":"72.4"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-correction-on-conll-2014","task":"Grammatical Error Correction","dataset":"CoNLL-2014 Shared Task","model":"Sequence tagging + token-level transformations + two-stage fine-tuning (+BERT, RoBERTa, XLNet)","rank_in_archive_order":10,"of":23,"metrics":{"F0.5":"66.5","Precision":"78.2","Recall":"41.5"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-correction-on-conll-2014","task":"Grammatical Error Correction","dataset":"CoNLL-2014 Shared Task","model":"Sequence tagging + token-level transformations + two-stage fine-tuning (+XLNet)","rank_in_archive_order":12,"of":23,"metrics":{"F0.5":"65.3","Precision":"77.5","Recall":"40.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.12592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.12592"}},"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/psawa/gecko-app","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/grammarly/gector","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gotutiyan/gector","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":1,"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"repositories":1},"listed":{"samples":2,"ran":2,"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":"eacea3a25d6b9838","entry":"need_add_prefix_space","repo":"gotutiyan/gector","repo_kind":"listed","path":"src/gector/cli/predict.py","file_url":"https://github.com/gotutiyan/gector/blob/HEAD/src/gector/cli/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eacea3a25d6b9838"}},{"code_sha256_prefix":"0f854050e3b7af65","entry":"visualizer","repo":"gotutiyan/gector","repo_kind":"listed","path":"src/gector/cli/predict.py","file_url":"https://github.com/gotutiyan/gector/blob/HEAD/src/gector/cli/predict.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":"0f854050e3b7af65"}},{"code_sha256_prefix":"94f13ee8c30ce76f","entry":"annotate_fce_doc","repo":"grammarly/gector","repo_kind":"official","path":"utils/prepare_clc_fce_data.py","file_url":"https://github.com/grammarly/gector/blob/HEAD/utils/prepare_clc_fce_data.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":"94f13ee8c30ce76f"}},{"code_sha256_prefix":"e2be5e9c2082d301","entry":"apply_merge_transformation","repo":"grammarly/gector","repo_kind":"official","path":"utils/preprocess_data.py","file_url":"https://github.com/grammarly/gector/blob/HEAD/utils/preprocess_data.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":"e2be5e9c2082d301"}},{"code_sha256_prefix":"9a10dedeb0b5dac7","entry":"convert_fce","repo":"grammarly/gector","repo_kind":"official","path":"utils/prepare_clc_fce_data.py","file_url":"https://github.com/grammarly/gector/blob/HEAD/utils/prepare_clc_fce_data.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":"9a10dedeb0b5dac7"}},{"code_sha256_prefix":"87468610676c6dd6","entry":"convert_using_case","repo":"grammarly/gector","repo_kind":"official","path":"utils/helpers.py","file_url":"https://github.com/grammarly/gector/blob/HEAD/utils/helpers.py","link_basis":"harvester_set","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":"87468610676c6dd6"}},{"code_sha256_prefix":"fc4f0a3954e20959","entry":"filter_line","repo":"grammarly/gector","repo_kind":"official","path":"utils/filter_brackets.py","file_url":"https://github.com/grammarly/gector/blob/HEAD/utils/filter_brackets.py","link_basis":"harvester_set","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":"fc4f0a3954e20959"}},{"code_sha256_prefix":"6f0e771498f45ff4","entry":"get_bpe_groups","repo":"grammarly/gector","repo_kind":"official","path":"gector/tokenization.py","file_url":"https://github.com/grammarly/gector/blob/HEAD/gector/tokenization.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":"6f0e771498f45ff4"}},{"code_sha256_prefix":"e465d1ef5c3c98db","entry":"get_offsets_and_reduce_input_ids","repo":"grammarly/gector","repo_kind":"official","path":"gector/tokenization.py","file_url":"https://github.com/grammarly/gector/blob/HEAD/gector/tokenization.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":"e465d1ef5c3c98db"}},{"code_sha256_prefix":"395b7b304d288571","entry":"get_target_sent_by_edits","repo":"grammarly/gector","repo_kind":"official","path":"utils/helpers.py","file_url":"https://github.com/grammarly/gector/blob/HEAD/utils/helpers.py","link_basis":"harvester_set","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":"395b7b304d288571"}},{"code_sha256_prefix":"3b89561b72017ad9","entry":"reduce_input_ids","repo":"grammarly/gector","repo_kind":"official","path":"gector/tokenization.py","file_url":"https://github.com/grammarly/gector/blob/HEAD/gector/tokenization.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":"3b89561b72017ad9"}},{"code_sha256_prefix":"fa83b5a1840e54e0","entry":"replace_merge_transforms","repo":"grammarly/gector","repo_kind":"official","path":"utils/helpers.py","file_url":"https://github.com/grammarly/gector/blob/HEAD/utils/helpers.py","link_basis":"harvester_set","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":"fa83b5a1840e54e0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}