Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386257570> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4386257570 abstract "Different languages are subject to several types of spelling mistakes. In this paper, we use a deep neural network machine learning model called transformer to correct wide range of Arabic soft spelling mistakes including: lexical and semantic errors (due to the sound of the letter), keyboard errors (due to the character position on the keyboard), common typing errors (like deleting space, preposition errors, and third pronoun errors), and some random typing errors when the user replaces a letter with some other letter. Our approach has two stages: first, we use huge Wiki-40B dataset of Arabic texts which is error free. We inject this dataset with synthetic targeted errors, then we perform training and testing on this dataset. In the second stage, we use the training weights of the first stage to perform training and testing on a dataset that we have collected for this purpose, which contains real Arabic spelling mistakes. We call this dataset REALMS, which stands for REal Arabic Language Mistakes in Spelling. The proposed model can correct 99.12% of the artificial errors that were injected into the Wiki-40B dataset. Additionally, it achieves a character error rate of 1.14% and accuracy of 98.85% on the REALMS dataset." @default.
- W4386257570 created "2023-08-30" @default.
- W4386257570 creator A5004562640 @default.
- W4386257570 creator A5036769756 @default.
- W4386257570 date "2023-08-09" @default.
- W4386257570 modified "2023-09-27" @default.
- W4386257570 title "Correcting Wide-Range of Arabic Spelling Mistakes Using Machine Learning and Transformers" @default.
- W4386257570 cites W2945743195 @default.
- W4386257570 cites W3034797320 @default.
- W4386257570 cites W3041181542 @default.
- W4386257570 cites W3164045210 @default.
- W4386257570 cites W3186062448 @default.
- W4386257570 cites W3192770664 @default.
- W4386257570 cites W3196313137 @default.
- W4386257570 cites W4200101290 @default.
- W4386257570 cites W4308861787 @default.
- W4386257570 doi "https://doi.org/10.1109/icit58056.2023.10225830" @default.
- W4386257570 hasPublicationYear "2023" @default.
- W4386257570 type Work @default.
- W4386257570 citedByCount "0" @default.
- W4386257570 crossrefType "proceedings-article" @default.
- W4386257570 hasAuthorship W4386257570A5004562640 @default.
- W4386257570 hasAuthorship W4386257570A5036769756 @default.
- W4386257570 hasConcept C121332964 @default.
- W4386257570 hasConcept C138885662 @default.
- W4386257570 hasConcept C154945302 @default.
- W4386257570 hasConcept C165801399 @default.
- W4386257570 hasConcept C204321447 @default.
- W4386257570 hasConcept C2524010 @default.
- W4386257570 hasConcept C2777801307 @default.
- W4386257570 hasConcept C2780861071 @default.
- W4386257570 hasConcept C28490314 @default.
- W4386257570 hasConcept C33923547 @default.
- W4386257570 hasConcept C40969351 @default.
- W4386257570 hasConcept C41008148 @default.
- W4386257570 hasConcept C41895202 @default.
- W4386257570 hasConcept C62520636 @default.
- W4386257570 hasConcept C66322947 @default.
- W4386257570 hasConcept C96455323 @default.
- W4386257570 hasConceptScore W4386257570C121332964 @default.
- W4386257570 hasConceptScore W4386257570C138885662 @default.
- W4386257570 hasConceptScore W4386257570C154945302 @default.
- W4386257570 hasConceptScore W4386257570C165801399 @default.
- W4386257570 hasConceptScore W4386257570C204321447 @default.
- W4386257570 hasConceptScore W4386257570C2524010 @default.
- W4386257570 hasConceptScore W4386257570C2777801307 @default.
- W4386257570 hasConceptScore W4386257570C2780861071 @default.
- W4386257570 hasConceptScore W4386257570C28490314 @default.
- W4386257570 hasConceptScore W4386257570C33923547 @default.
- W4386257570 hasConceptScore W4386257570C40969351 @default.
- W4386257570 hasConceptScore W4386257570C41008148 @default.
- W4386257570 hasConceptScore W4386257570C41895202 @default.
- W4386257570 hasConceptScore W4386257570C62520636 @default.
- W4386257570 hasConceptScore W4386257570C66322947 @default.
- W4386257570 hasConceptScore W4386257570C96455323 @default.
- W4386257570 hasLocation W43862575701 @default.
- W4386257570 hasOpenAccess W4386257570 @default.
- W4386257570 hasPrimaryLocation W43862575701 @default.
- W4386257570 hasRelatedWork W1653505924 @default.
- W4386257570 hasRelatedWork W1993118056 @default.
- W4386257570 hasRelatedWork W2075207372 @default.
- W4386257570 hasRelatedWork W2279095437 @default.
- W4386257570 hasRelatedWork W2313713951 @default.
- W4386257570 hasRelatedWork W2621757255 @default.
- W4386257570 hasRelatedWork W2892009249 @default.
- W4386257570 hasRelatedWork W4200101290 @default.
- W4386257570 hasRelatedWork W4380189709 @default.
- W4386257570 hasRelatedWork W3140870753 @default.
- W4386257570 isParatext "false" @default.
- W4386257570 isRetracted "false" @default.
- W4386257570 workType "article" @default.