Matches in SemOpenAlex for { <https://semopenalex.org/work/W3116890009> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3116890009 endingPage "315" @default.
- W3116890009 startingPage "303" @default.
- W3116890009 abstract "The automatic correction of grammar and spelling errors is important for students, second language learners, and some Natural Language Processing (NLP) tasks such as part of speech and text summarization. Recently, Neural Machine Translation (NMT) has been an out-performing and well-established model in the task of Grammar Error Correction (GEC). Arabic GEC is still growing because of some challenges, such as scarcity of training sets and the complexity of Arabic language. To overcome these issues, we introduced an unsupervised method to generate large-scale synthetic training data based on confusion function to increase the amount of training set. Furthermore, we introduced a supervised NMT model for AGEC called SCUT AGEC. SCUT AGEC is a convolutional sequence-to-sequence model consisting of nine encoder-decoder layers with attention mechanism. We applied fine-tuning to improve the performance and get more efficient results. Convolutional Neural Networks (CNN) gives our model ability to joint feature extraction and classification in one task and we proved that it is an efficient way to capture features of the local context. Moreover, it is easy to obtain long-term dependencies because of convolutional layers staking. Our proposed model becomes the first supervised AGEC system based on the convolutional sequence-to-sequence learning to outperforms the current state-of-the-art neural AGEC models." @default.
- W3116890009 created "2021-01-05" @default.
- W3116890009 creator A5017777141 @default.
- W3116890009 creator A5035133018 @default.
- W3116890009 creator A5036400689 @default.
- W3116890009 creator A5060529705 @default.
- W3116890009 creator A5081065040 @default.
- W3116890009 creator A5091580960 @default.
- W3116890009 date "2021-09-01" @default.
- W3116890009 modified "2023-09-25" @default.
- W3116890009 title "Synthetic data with neural machine translation for automatic correction in arabic grammar" @default.
- W3116890009 cites W2064675550 @default.
- W3116890009 cites W2146574666 @default.
- W3116890009 cites W2250201117 @default.
- W3116890009 cites W2250305510 @default.
- W3116890009 cites W2250384164 @default.
- W3116890009 cites W2251094914 @default.
- W3116890009 cites W2251363456 @default.
- W3116890009 cites W2470324779 @default.
- W3116890009 cites W2493916176 @default.
- W3116890009 cites W2890230387 @default.
- W3116890009 cites W2916043108 @default.
- W3116890009 cites W2945635251 @default.
- W3116890009 cites W2948335087 @default.
- W3116890009 cites W2962784628 @default.
- W3116890009 cites W2962863357 @default.
- W3116890009 cites W2964187553 @default.
- W3116890009 cites W2971064282 @default.
- W3116890009 cites W3018086583 @default.
- W3116890009 cites W3089057597 @default.
- W3116890009 doi "https://doi.org/10.1016/j.eij.2020.12.001" @default.
- W3116890009 hasPublicationYear "2021" @default.
- W3116890009 type Work @default.
- W3116890009 sameAs 3116890009 @default.
- W3116890009 citedByCount "13" @default.
- W3116890009 countsByYear W31168900092021 @default.
- W3116890009 countsByYear W31168900092022 @default.
- W3116890009 countsByYear W31168900092023 @default.
- W3116890009 crossrefType "journal-article" @default.
- W3116890009 hasAuthorship W3116890009A5017777141 @default.
- W3116890009 hasAuthorship W3116890009A5035133018 @default.
- W3116890009 hasAuthorship W3116890009A5036400689 @default.
- W3116890009 hasAuthorship W3116890009A5060529705 @default.
- W3116890009 hasAuthorship W3116890009A5081065040 @default.
- W3116890009 hasAuthorship W3116890009A5091580960 @default.
- W3116890009 hasBestOaLocation W31168900091 @default.
- W3116890009 hasConcept C138885662 @default.
- W3116890009 hasConcept C151730666 @default.
- W3116890009 hasConcept C154945302 @default.
- W3116890009 hasConcept C203005215 @default.
- W3116890009 hasConcept C204321447 @default.
- W3116890009 hasConcept C26022165 @default.
- W3116890009 hasConcept C2779343474 @default.
- W3116890009 hasConcept C28490314 @default.
- W3116890009 hasConcept C41008148 @default.
- W3116890009 hasConcept C41895202 @default.
- W3116890009 hasConcept C81363708 @default.
- W3116890009 hasConcept C86803240 @default.
- W3116890009 hasConceptScore W3116890009C138885662 @default.
- W3116890009 hasConceptScore W3116890009C151730666 @default.
- W3116890009 hasConceptScore W3116890009C154945302 @default.
- W3116890009 hasConceptScore W3116890009C203005215 @default.
- W3116890009 hasConceptScore W3116890009C204321447 @default.
- W3116890009 hasConceptScore W3116890009C26022165 @default.
- W3116890009 hasConceptScore W3116890009C2779343474 @default.
- W3116890009 hasConceptScore W3116890009C28490314 @default.
- W3116890009 hasConceptScore W3116890009C41008148 @default.
- W3116890009 hasConceptScore W3116890009C41895202 @default.
- W3116890009 hasConceptScore W3116890009C81363708 @default.
- W3116890009 hasConceptScore W3116890009C86803240 @default.
- W3116890009 hasIssue "3" @default.
- W3116890009 hasLocation W31168900091 @default.
- W3116890009 hasLocation W31168900092 @default.
- W3116890009 hasOpenAccess W3116890009 @default.
- W3116890009 hasPrimaryLocation W31168900091 @default.
- W3116890009 hasRelatedWork W1484029852 @default.
- W3116890009 hasRelatedWork W1512718085 @default.
- W3116890009 hasRelatedWork W1569841287 @default.
- W3116890009 hasRelatedWork W2094861944 @default.
- W3116890009 hasRelatedWork W2167662847 @default.
- W3116890009 hasRelatedWork W3171566221 @default.
- W3116890009 hasRelatedWork W3198474835 @default.
- W3116890009 hasRelatedWork W4379525811 @default.
- W3116890009 hasRelatedWork W4385863891 @default.
- W3116890009 hasRelatedWork W2610387714 @default.
- W3116890009 hasVolume "22" @default.
- W3116890009 isParatext "false" @default.
- W3116890009 isRetracted "false" @default.
- W3116890009 magId "3116890009" @default.
- W3116890009 workType "article" @default.