Deep Learning for Arabic Error Detection and Correction

Research on tools for automating the proofreading of Arabic text has received much attention in recent years. There is an increasing demand for applications that can detect and correct Arabic spelling and grammatical errors to improve the quality of Arabic text content and application input. Our rev...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: ALKHATIB, MANAR (author)
مؤلفون آخرون: ABDEL MONEM, AZZA (author), SHAALAN, KHALED (author)
منشور في: 2020
الموضوعات:
الوصول للمادة أونلاين:https://bspace.buid.ac.ae/handle/1234/2793
https://doi.org/10.1145/3373266.
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1862980613878841344
author ALKHATIB, MANAR
author2 ABDEL MONEM, AZZA
SHAALAN, KHALED
author2_role author
author
author_facet ALKHATIB, MANAR
ABDEL MONEM, AZZA
SHAALAN, KHALED
author_role author
dc.creator.none.fl_str_mv ALKHATIB, MANAR
ABDEL MONEM, AZZA
SHAALAN, KHALED
dc.date.none.fl_str_mv 2020
2025-02-11T04:43:39Z
2025-02-11T04:43:39Z
dc.identifier.none.fl_str_mv Alkhatib, M., Monem, A.A. and Shaalan, K. (2020) “Deep Learning for Arabic Error Detection and Correction,” ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), 19(5), pp. 1–13.
2375-4699, 2375-4702
https://bspace.buid.ac.ae/handle/1234/2793
https://doi.org/10.1145/3373266.
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv ACM digital library
dc.relation.none.fl_str_mv ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)v19 n5 (20200812): 1-13
dc.subject.none.fl_str_mv CCS Concepts: • Computing methodologies → Machine learning; Machine learning approaches; Neural networks; Additional Key Words and Phrases: Error detection, error correction, bidirectional long short-term memory, word embedding, polynomial network classifier
dc.title.none.fl_str_mv Deep Learning for Arabic Error Detection and Correction
dc.type.none.fl_str_mv Article
description Research on tools for automating the proofreading of Arabic text has received much attention in recent years. There is an increasing demand for applications that can detect and correct Arabic spelling and grammatical errors to improve the quality of Arabic text content and application input. Our review of previous studies indicates that few Arabic spell-checking research efforts appropriately address the detection and correction of ill-formed words that do not conform to the Arabic morphology system. Even fewer systems address the detection and correction of erroneous well-formed Arabic words that are either contextually or semantically inconsistent within the text. We introduce an approach that investigates employing deep neural network technology for error detection in Arabic text. We have developed a systematic framework for spelling and grammar error detection, as well as correction at the word level, based on a bidirectional long short-term memory mechanism and word embedding, in which a polynomial network classifier is at the top of the sys tem. To get conclusive results, we have developed the most significant gold standard annotated corpus to date, containing 15 million fully inflected Arabic words. The data were collected from diverse text sources and genres, in which every erroneous and ill-formed word has been annotated, validated, and manually re vised by Arabic specialists. This valuable asset is available for the Arabic natural language processing research community. The experimental results confirm that our proposed system significantly outperforms the per formance of Microsoft Word 2013 and Open Office Ayaspell 3.4, which have been used in the literature for evaluating similar research.
id budr_4d73d25a7ba04a74d78a68dad0517f89
identifier_str_mv Alkhatib, M., Monem, A.A. and Shaalan, K. (2020) “Deep Learning for Arabic Error Detection and Correction,” ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), 19(5), pp. 1–13.
2375-4699, 2375-4702
language_invalid_str_mv en
network_acronym_str budr
network_name_str The British University in Dubai repository
oai_identifier_str oai:bspace.buid.ac.ae:1234/2793
publishDate 2020
publisher.none.fl_str_mv ACM digital library
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Deep Learning for Arabic Error Detection and CorrectionALKHATIB, MANARABDEL MONEM, AZZASHAALAN, KHALEDCCS Concepts: • Computing methodologies → Machine learning; Machine learning approaches; Neural networks; Additional Key Words and Phrases: Error detection, error correction, bidirectional long short-term memory, word embedding, polynomial network classifierResearch on tools for automating the proofreading of Arabic text has received much attention in recent years. There is an increasing demand for applications that can detect and correct Arabic spelling and grammatical errors to improve the quality of Arabic text content and application input. Our review of previous studies indicates that few Arabic spell-checking research efforts appropriately address the detection and correction of ill-formed words that do not conform to the Arabic morphology system. Even fewer systems address the detection and correction of erroneous well-formed Arabic words that are either contextually or semantically inconsistent within the text. We introduce an approach that investigates employing deep neural network technology for error detection in Arabic text. We have developed a systematic framework for spelling and grammar error detection, as well as correction at the word level, based on a bidirectional long short-term memory mechanism and word embedding, in which a polynomial network classifier is at the top of the sys tem. To get conclusive results, we have developed the most significant gold standard annotated corpus to date, containing 15 million fully inflected Arabic words. The data were collected from diverse text sources and genres, in which every erroneous and ill-formed word has been annotated, validated, and manually re vised by Arabic specialists. This valuable asset is available for the Arabic natural language processing research community. The experimental results confirm that our proposed system significantly outperforms the per formance of Microsoft Word 2013 and Open Office Ayaspell 3.4, which have been used in the literature for evaluating similar research.ACM digital library2025-02-11T04:43:39Z2025-02-11T04:43:39Z2020ArticleAlkhatib, M., Monem, A.A. and Shaalan, K. (2020) “Deep Learning for Arabic Error Detection and Correction,” ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), 19(5), pp. 1–13.2375-4699, 2375-4702https://bspace.buid.ac.ae/handle/1234/2793https://doi.org/10.1145/3373266.enACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)v19 n5 (20200812): 1-13oai:bspace.buid.ac.ae:1234/27932026-01-29T17:14:01Z
spellingShingle Deep Learning for Arabic Error Detection and Correction
ALKHATIB, MANAR
CCS Concepts: • Computing methodologies → Machine learning; Machine learning approaches; Neural networks; Additional Key Words and Phrases: Error detection, error correction, bidirectional long short-term memory, word embedding, polynomial network classifier
title Deep Learning for Arabic Error Detection and Correction
title_full Deep Learning for Arabic Error Detection and Correction
title_fullStr Deep Learning for Arabic Error Detection and Correction
title_full_unstemmed Deep Learning for Arabic Error Detection and Correction
title_short Deep Learning for Arabic Error Detection and Correction
title_sort Deep Learning for Arabic Error Detection and Correction
topic CCS Concepts: • Computing methodologies → Machine learning; Machine learning approaches; Neural networks; Additional Key Words and Phrases: Error detection, error correction, bidirectional long short-term memory, word embedding, polynomial network classifier
url https://bspace.buid.ac.ae/handle/1234/2793
https://doi.org/10.1145/3373266.