DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kwon, Soonchoul | - |
dc.contributor.author | Lee, Gary Geunbae | - |
dc.date.accessioned | 2023-02-20T02:20:40Z | - |
dc.date.available | 2023-02-20T02:20:40Z | - |
dc.date.created | 2023-02-02 | - |
dc.date.issued | 2023-01 | - |
dc.identifier.issn | 0885-2308 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/115280 | - |
dc.description.abstract | © 2022 Elsevier LtdGrammatical error correction (GEC) has been successful with deep and complex neural machine translation models, but the annotated data to train the model are scarce. We propose a novel self-feeding training method that generates incorrect sentences from freely available correct sentences. The proposed training method can generate appropriate wrong sentences from unlabeled sentences, using a data generation model trained as an autoencoder. It can also add artificial noise to correct sentences to automatically generate incorrect sentences. We show that the GEC models trained with the self-feeding training method are successful without extra annotated data or deeper neural network-based models, achieving F0.5 score of 0.5982 on the CoNLL-2014 Shared Task test data with a transformer model. The results also show that fully unlabeled training is possible for data-scarce domains and languages. | - |
dc.language | English | - |
dc.publisher | Academic Press | - |
dc.relation.isPartOf | Computer Speech and Language | - |
dc.title | Self-feeding training method for semi-supervised grammatical error correction | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.csl.2022.101435 | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | Computer Speech and Language, v.77 | - |
dc.identifier.wosid | 000858986000002 | - |
dc.citation.title | Computer Speech and Language | - |
dc.citation.volume | 77 | - |
dc.contributor.affiliatedAuthor | Kwon, Soonchoul | - |
dc.contributor.affiliatedAuthor | Lee, Gary Geunbae | - |
dc.identifier.scopusid | 2-s2.0-85136125143 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.type.docType | Article | - |
dc.subject.keywordAuthor | Data augmentation | - |
dc.subject.keywordAuthor | Grammatical error correction | - |
dc.subject.keywordAuthor | Natural language processing | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.