{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T15:20:20Z","timestamp":1769527220486,"version":"3.49.0"},"reference-count":47,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T00:00:00Z","timestamp":1720137600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application","award":["No. 2022B1212010011"],"award-info":[{"award-number":["No. 2022B1212010011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Grammar error correction systems are pivotal in the field of natural language processing (NLP), with a primary focus on identifying and correcting the grammatical integrity of written text. This is crucial for both language learning and formal communication. Recently, neural machine translation (NMT) has emerged as a promising approach in high demand. However, this approach faces significant challenges, particularly the scarcity of training data and the complexity of grammar error correction (GEC), especially for low-resource languages such as Indonesian. To address these challenges, we propose InSpelPoS, a confusion method that combines two synthetic data generation methods: the Inverted Spellchecker and Patterns+POS. Furthermore, we introduce an adapted seq2seq framework equipped with a dynamic decoding method and state-of-the-art Transformer-based neural language models to enhance the accuracy and efficiency of GEC. The dynamic decoding method is capable of navigating the complexities of GEC and correcting a wide range of errors, including contextual and grammatical errors. The proposed model leverages the contextual information of words and sentences to generate a corrected output. To assess the effectiveness of our proposed framework, we conducted experiments using synthetic data and compared its performance with existing GEC systems. The results demonstrate a significant improvement in the accuracy of Indonesian GEC compared to existing methods.<\/jats:p>","DOI":"10.7717\/peerj-cs.2122","type":"journal-article","created":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T07:14:21Z","timestamp":1720163661000},"page":"e2122","source":"Crossref","is-referenced-by-count":4,"title":["Dynamic decoding and dual synthetic data for automatic correction of grammar in low-resource scenario"],"prefix":"10.7717","volume":"10","author":[{"given":"Ahmad","family":"Musyafa","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"},{"name":"Department of Informatics Engineering, Pamulang University, South Tangerang, Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aiman","family":"Solyman","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Milan, Milan, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siraj","family":"Khan","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wentian","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Faizan","family":"Khan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2024,7,5]]},"reference":[{"key":"10.7717\/peerj-cs.2122\/ref-1","doi-asserted-by":"publisher","first-page":"7226","DOI":"10.18653\/v1\/2022.acl-long.500","article-title":"One country, 700+ languages: NLP challenges for underrepresented languages and dialects in Indonesia","author":"Aji","year":"2022"},{"key":"10.7717\/peerj-cs.2122\/ref-2","doi-asserted-by":"publisher","first-page":"52","DOI":"10.18653\/v1\/W19-4406","article-title":"The BEA-2019 shared task on grammatical error correction","author":"Bryant","year":"2019"},{"issue":"5","key":"10.7717\/peerj-cs.2122\/ref-3","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1145\/3574130","article-title":"Rule based fuzzy computing approach on self-supervised sentiment polarity classification with word sense disambiguation in machine translation for hindi language","volume":"22","author":"Chauhan","year":"2023","journal-title":"ACM Transactions on Asian and Low-Resource Language Information Processing"},{"key":"10.7717\/peerj-cs.2122\/ref-4","doi-asserted-by":"publisher","first-page":"213","DOI":"10.18653\/v1\/W19-4423","article-title":"A neural grammatical error correction system built on better pre-training and sequential transfer learning","author":"Choe","year":"2019"},{"key":"10.7717\/peerj-cs.2122\/ref-5","doi-asserted-by":"publisher","first-page":"8440","DOI":"10.18653\/v1\/2020.acl-main.747","article-title":"Unsupervised cross-lingual representation learning at scale","author":"Conneau","year":"2020"},{"key":"10.7717\/peerj-cs.2122\/ref-6","first-page":"568","article-title":"Better evaluation for grammatical error correction","author":"Dahlmeier","year":"2012"},{"key":"10.7717\/peerj-cs.2122\/ref-7","article-title":"Statistical machine translation for indic languages","author":"Das","year":"2023"},{"key":"10.7717\/peerj-cs.2122\/ref-8","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.18653\/v1\/N19-1423","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.7717\/peerj-cs.2122\/ref-9","doi-asserted-by":"publisher","first-page":"15","DOI":"10.3115\/v1\/W14-1702","article-title":"Grammatical error correction using hybrid systems and type filtering","author":"Felice","year":"2014"},{"key":"10.7717\/peerj-cs.2122\/ref-10","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.18653\/v1\/P18-1097","article-title":"Fluency boost learning and inference for neural grammatical error correction","author":"Ge","year":"2018"},{"key":"10.7717\/peerj-cs.2122\/ref-11","article-title":"Ranked: The 100 most spoken languages around the world. Visual Capitalist","author":"Ghosh","year":"2020"},{"key":"10.7717\/peerj-cs.2122\/ref-12","doi-asserted-by":"publisher","first-page":"252","DOI":"10.18653\/v1\/W19-4427","article-title":"Neural grammatical error correction systems with unsupervised pre-training on synthetic data","author":"Grundkiewicz","year":"2019"},{"issue":"14","key":"10.7717\/peerj-cs.2122\/ref-13","doi-asserted-by":"publisher","first-page":"i295","DOI":"10.1093\/bioinformatics\/btz375","article-title":"LinearFold: linear-time approximate RNA folding by 5\u2019-to-3\u2019dynamic programming and beam search","volume":"35","author":"Huang","year":"2019","journal-title":"Bioinformatics"},{"key":"10.7717\/peerj-cs.2122\/ref-14","doi-asserted-by":"publisher","first-page":"4977","DOI":"10.18653\/v1\/D18-1541","article-title":"Wronging a right: generating better errors to improve grammatical error detection","author":"Kasewa","year":"2018"},{"key":"10.7717\/peerj-cs.2122\/ref-15","first-page":"6","article-title":"A method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"10.7717\/peerj-cs.2122\/ref-16","first-page":"598","article-title":"Liputan6: a large-scale indonesian dataset for text summarization","author":"Koto","year":"2020"},{"key":"10.7717\/peerj-cs.2122\/ref-17","first-page":"40","article-title":"Overview of NLP-TEA 2016 shared task for chinese grammatical error diagnosis","author":"Lee","year":"2016"},{"key":"10.7717\/peerj-cs.2122\/ref-18","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.18653\/v1\/2022.findings-emnlp.109","article-title":"Residual learning of neural text generation with n-gram language model","author":"Li","year":"2022"},{"key":"10.7717\/peerj-cs.2122\/ref-19","doi-asserted-by":"publisher","first-page":"3291","DOI":"10.18653\/v1\/N19-1333","article-title":"Corpora generation for grammatical error correction","author":"Lichtarge","year":"2019"},{"issue":"4","key":"10.7717\/peerj-cs.2122\/ref-20","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1145\/3440993","article-title":"A framework for indonesian grammar error correction","volume":"20","author":"Lin","year":"2021","journal-title":"ACM Transactions on Asian and Low-Resource Language Information Processing"},{"key":"10.7717\/peerj-cs.2122\/ref-21","article-title":"A BERT-based unsupervised grammatical error correction framework","author":"Lin","year":"2023"},{"key":"10.7717\/peerj-cs.2122\/ref-22","first-page":"411","article-title":"Agreement on target-bidirectional neural machine translation","author":"Liu","year":"2016"},{"key":"10.7717\/peerj-cs.2122\/ref-23","doi-asserted-by":"publisher","first-page":"e1639","DOI":"10.7717\/peerj-cs.1639","article-title":"Semi-supervised learning and bidirectional decoding for effective grammar correction in low-resource scenarios","volume":"9","author":"Mahmoud","year":"2023","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.2122\/ref-24","first-page":"2795","article-title":"Subword segmental machine translation: unifying segmentation and target sentence generation","author":"Meyer","year":"2023"},{"key":"10.7717\/peerj-cs.2122\/ref-25","doi-asserted-by":"publisher","first-page":"39","DOI":"10.3115\/v1\/W14-3605","article-title":"The first QALB shared task on automatic text correction for arabic","author":"Mohit","year":"2014"},{"issue":"20","key":"10.7717\/peerj-cs.2122\/ref-26","doi-asserted-by":"publisher","first-page":"10380","DOI":"10.3390\/app122010380","article-title":"Automatic correction of indonesian grammatical errors based on transformer","volume":"12","author":"Musyafa","year":"2022","journal-title":"Applied Sciences"},{"key":"10.7717\/peerj-cs.2122\/ref-27","doi-asserted-by":"publisher","first-page":"346","DOI":"10.18653\/v1\/D19-5545","article-title":"Grammatical error correction in low-resource scenarios","author":"N\u00e1plava","year":"2019"},{"key":"10.7717\/peerj-cs.2122\/ref-28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3115\/v1\/W14-1701","article-title":"The CoNLL-2014 shared task on grammatical error correction","author":"Ng","year":"2014"},{"key":"10.7717\/peerj-cs.2122\/ref-29","first-page":"1","article-title":"Bert multilingual and capsule network for arabic sentiment analysis","author":"Obied","year":"2021"},{"key":"10.7717\/peerj-cs.2122\/ref-30","first-page":"114","article-title":"A low-resource approach to the grammatical error correction of Ukrainian","author":"Palma\u00a0Gomez","year":"2023"},{"key":"10.7717\/peerj-cs.2122\/ref-31","doi-asserted-by":"publisher","first-page":"311","DOI":"10.3115\/1073083.1073135","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.7717\/peerj-cs.2122\/ref-32","doi-asserted-by":"publisher","first-page":"702","DOI":"10.18653\/v1\/2021.acl-short.89","article-title":"A simple recipe for multilingual grammatical error correction","author":"Rothe","year":"2021"},{"key":"10.7717\/peerj-cs.2122\/ref-33","doi-asserted-by":"publisher","first-page":"242","DOI":"10.18653\/v1\/W16-0528","article-title":"Sentence-level grammatical error identification as sequence-to-sequence correction","author":"Schmaltz","year":"2016"},{"key":"10.7717\/peerj-cs.2122\/ref-34","doi-asserted-by":"publisher","first-page":"86","DOI":"10.18653\/v1\/P16-1009","article-title":"Improving neural machine translation models with monolingual data","author":"Sennrich","year":"2016"},{"key":"10.7717\/peerj-cs.2122\/ref-35","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.18653\/v1\/P16-1162","article-title":"Neural machine translation of rare words with subword units","author":"Sennrich","year":"2016"},{"key":"10.7717\/peerj-cs.2122\/ref-36","first-page":"1","article-title":"Proposed model for arabic grammar error correction based on convolutional neural network","author":"Solyman","year":"2019"},{"key":"10.7717\/peerj-cs.2122\/ref-37","doi-asserted-by":"publisher","first-page":"108180","DOI":"10.1016\/j.knosys.2022.108180","article-title":"Automatic Arabic grammatical error correction based on expectation-maximization routing and target-bidirectional agreement","volume":"241","author":"Solyman","year":"2022","journal-title":"Knowledge-Based Systems"},{"issue":"6","key":"10.7717\/peerj-cs.2122\/ref-38","doi-asserted-by":"publisher","first-page":"101572","DOI":"10.1016\/j.jksuci.2023.101572","article-title":"Optimizing the impact of data augmentation for low-resource grammatical error correction","volume":"35","author":"Solyman","year":"2023","journal-title":"Journal of King Saud University\u2014Computer and Information Sciences"},{"issue":"3","key":"10.7717\/peerj-cs.2122\/ref-39","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.eij.2020.12.001","article-title":"Synthetic data with neural machine translation for automatic correction in arabic grammar","volume":"22","author":"Solyman","year":"2021","journal-title":"Egyptian Informatics Journal"},{"key":"10.7717\/peerj-cs.2122\/ref-40","doi-asserted-by":"publisher","first-page":"168","DOI":"10.18653\/v1\/W19-4417","article-title":"The CUED\u2019s grammatical error correction systems for BEA-2019","author":"Stahlberg","year":"2019"},{"key":"10.7717\/peerj-cs.2122\/ref-41","first-page":"37","article-title":"Synthetic data generation for grammatical error correction with tagged corruption models","author":"Stahlberg","year":"2021"},{"key":"10.7717\/peerj-cs.2122\/ref-42","doi-asserted-by":"publisher","first-page":"27","DOI":"10.18653\/v1\/2020.acl-srw.5","article-title":"Grammatical error correction using pseudo learner corpus considering learner\u2019s error tendency","author":"Takahashi","year":"2020"},{"key":"10.7717\/peerj-cs.2122\/ref-43","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.7717\/peerj-cs.2122\/ref-44","article-title":"CCNet: extracting high quality monolingual datasets from web crawl data","author":"Wenzek","year":"2019"},{"key":"10.7717\/peerj-cs.2122\/ref-45","doi-asserted-by":"publisher","first-page":"198","DOI":"10.18653\/v1\/2020.bea-1.21","article-title":"A comparative study of synthetic data generation methods for grammatical error correction","author":"White","year":"2020"},{"key":"10.7717\/peerj-cs.2122\/ref-46","article-title":"Neural language correction with character-based attention","author":"Xie","year":"2016"},{"key":"10.7717\/peerj-cs.2122\/ref-47","doi-asserted-by":"publisher","first-page":"619","DOI":"10.18653\/v1\/N18-1057","article-title":"Noising and denoising natural language: diverse backtranslation for grammar correction","author":"Xie","year":"2018"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-2122.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2122.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2122.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2122.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T07:14:29Z","timestamp":1720163669000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-2122"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,5]]},"references-count":47,"alternative-id":["10.7717\/peerj-cs.2122"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.2122","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,5]]},"article-number":"e2122"}}