{"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/neural-grammatical-error-correction-systems","title":"Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data","arxiv_id":null,"date":"2019-08-01","proceeding":"WS 2019 8","authors":["Roman Grundkiewicz","Marcin Junczys-Dowmunt","Kenneth Heafield"],"abstract":"Considerable effort has been made to address the data sparsity problem in neural grammatical error correction. In this work, we propose a simple and surprisingly effective unsupervised synthetic error generation method based on confusion sets extracted from a spellchecker to increase the amount of training data. Synthetic data is used to pre-train a Transformer sequence-to-sequence model, which not only improves over a strong baseline trained on authentic error-annotated data, but also enables the development of a practical GEC system in a scenario where little genuine error-annotated data is available. The developed systems placed first in the BEA19 shared task, achieving 69.47 and 64.24 F$_{0.5}$ in the restricted and low-resource tracks respectively, both on the W{\\&}I+LOCNESS test set. On the popular CoNLL 2014 test set, we report state-of-the-art results of 64.16 M{\\mbox{$^2$}} for the submitted system, and 61.30 M{\\mbox{$^2$}} for the constrained system trained on the NUCLE and Lang-8 data.","url_abs":"https://aclanthology.org/W19-4427","url_pdf":"https://aclanthology.org/W19-4427.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":"neural-grammatical-error-correction-systems","repo_url":"https://github.com/grammatical/pretraining-bea2019","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"grammatical-error-correction","task_name":"Grammatical Error Correction"},{"task_slug":"unsupervised-pre-training","task_name":"Unsupervised Pre-training"}],"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":"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":"Transformer","rank_in_archive_order":16,"of":19,"metrics":{"F0.5":"69.5"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}