Exploiting Functional Discourse Grammar to Enhance Complex Arabic Relation Extraction using a Hybrid Semantic Knowledge Base - Machine Learning Approach
Relation extraction from unstructured Arabic text is especially challenging due to the Arabic language com plex morphology and the variation in word semantics and lexical categories. The research documented in this paper presents a hybrid Semantic Knowledge base - Machine Learning (SKML) approach fo...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , |
| منشور في: |
2023
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://bspace.buid.ac.ae/handle/1234/2795 https://doi.org/10.1145/361058 |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1862980610945974272 |
|---|---|
| author | OSMAN, TAHA |
| author2 | KHALIL, HUSSEIN MILTAN, MOHAMMED SHAALAN, KHALED ALFRJANI, ROWIDA |
| author2_role | author author author author |
| author_facet | OSMAN, TAHA KHALIL, HUSSEIN MILTAN, MOHAMMED SHAALAN, KHALED ALFRJANI, ROWIDA |
| author_role | author |
| dc.creator.none.fl_str_mv | OSMAN, TAHA KHALIL, HUSSEIN MILTAN, MOHAMMED SHAALAN, KHALED ALFRJANI, ROWIDA |
| dc.date.none.fl_str_mv | 2023 2025-02-11T04:50:27Z 2025-02-11T04:50:27Z |
| dc.identifier.none.fl_str_mv | https://bspace.buid.ac.ae/handle/1234/2795 https://doi.org/10.1145/361058 |
| dc.language.none.fl_str_mv | en |
| dc.publisher.none.fl_str_mv | ACM digital library ACM digital library |
| dc.relation.none.fl_str_mv | ACM Transactions on Asian and Low-Resource Language Information Processing, Volume 22, Issue 8 Article No.: 214, Pages 1 - 30 |
| dc.subject.none.fl_str_mv | CCS Concepts: • Information systems → Information extraction; Additional Key Words and Phrases: Arabic relation extraction, Natural Language Processing, semantic web base, Functional Discourse Grammar, hybrid knowledge-based machine learning classification |
| dc.title.none.fl_str_mv | Exploiting Functional Discourse Grammar to Enhance Complex Arabic Relation Extraction using a Hybrid Semantic Knowledge Base - Machine Learning Approach |
| dc.type.none.fl_str_mv | Article |
| description | Relation extraction from unstructured Arabic text is especially challenging due to the Arabic language com plex morphology and the variation in word semantics and lexical categories. The research documented in this paper presents a hybrid Semantic Knowledge base - Machine Learning (SKML) approach for extracting complex Arabic relations from unstructured Arabic documents; the proposed approach exploits the princi ples of Functional Discourse Grammar (FDG) to emphasise the semantic and pragmatic properties of the language and facilitate the identification of relation elements. At the initial phase, the novel FDG-SKML re lation extraction approach deploys a lexical-based mechanism that utilises a purposely built domain-specific Semantic Knowledge to encode the semantic association between the identified relations’ elements. The eval uation of the initial stage evidenced improved accuracy for extracting most complex Arabic relations. The initial relation extraction mechanism was further extended by integrating its output into a Machine Learn ing classifier that facilitated extracting especially complex relations with significant disparity in the relation elements’ presence, order, and correlation. Using Economics as the problem domain, experimental evalua tion evidenced the high accuracy of our FDG-SKML approach in complex Arabic relation extraction task and demonstrated its further improvement upon integration with machine learning classifiers. |
| id | budr_6fd4f4da3a0efb888f0ac22465861071 |
| 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:1234/2795 |
| publishDate | 2023 |
| publisher.none.fl_str_mv | ACM digital library ACM digital library |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| spelling | Exploiting Functional Discourse Grammar to Enhance Complex Arabic Relation Extraction using a Hybrid Semantic Knowledge Base - Machine Learning ApproachOSMAN, TAHAKHALIL, HUSSEINMILTAN, MOHAMMEDSHAALAN, KHALEDALFRJANI, ROWIDACCS Concepts: • Information systems → Information extraction; Additional Key Words and Phrases: Arabic relation extraction, Natural Language Processing, semantic web base, Functional Discourse Grammar, hybrid knowledge-based machine learning classificationRelation extraction from unstructured Arabic text is especially challenging due to the Arabic language com plex morphology and the variation in word semantics and lexical categories. The research documented in this paper presents a hybrid Semantic Knowledge base - Machine Learning (SKML) approach for extracting complex Arabic relations from unstructured Arabic documents; the proposed approach exploits the princi ples of Functional Discourse Grammar (FDG) to emphasise the semantic and pragmatic properties of the language and facilitate the identification of relation elements. At the initial phase, the novel FDG-SKML re lation extraction approach deploys a lexical-based mechanism that utilises a purposely built domain-specific Semantic Knowledge to encode the semantic association between the identified relations’ elements. The eval uation of the initial stage evidenced improved accuracy for extracting most complex Arabic relations. The initial relation extraction mechanism was further extended by integrating its output into a Machine Learn ing classifier that facilitated extracting especially complex relations with significant disparity in the relation elements’ presence, order, and correlation. Using Economics as the problem domain, experimental evalua tion evidenced the high accuracy of our FDG-SKML approach in complex Arabic relation extraction task and demonstrated its further improvement upon integration with machine learning classifiers.ACM digital libraryACM digital library2025-02-11T04:50:27Z2025-02-11T04:50:27Z2023Articlehttps://bspace.buid.ac.ae/handle/1234/2795https://doi.org/10.1145/361058enACM Transactions on Asian and Low-Resource Language Information Processing, Volume 22, Issue 8 Article No.: 214, Pages 1 - 30oai:bspace.buid.ac.ae:1234/27952026-01-29T07:14:27Z |
| spellingShingle | Exploiting Functional Discourse Grammar to Enhance Complex Arabic Relation Extraction using a Hybrid Semantic Knowledge Base - Machine Learning Approach OSMAN, TAHA CCS Concepts: • Information systems → Information extraction; Additional Key Words and Phrases: Arabic relation extraction, Natural Language Processing, semantic web base, Functional Discourse Grammar, hybrid knowledge-based machine learning classification |
| title | Exploiting Functional Discourse Grammar to Enhance Complex Arabic Relation Extraction using a Hybrid Semantic Knowledge Base - Machine Learning Approach |
| title_full | Exploiting Functional Discourse Grammar to Enhance Complex Arabic Relation Extraction using a Hybrid Semantic Knowledge Base - Machine Learning Approach |
| title_fullStr | Exploiting Functional Discourse Grammar to Enhance Complex Arabic Relation Extraction using a Hybrid Semantic Knowledge Base - Machine Learning Approach |
| title_full_unstemmed | Exploiting Functional Discourse Grammar to Enhance Complex Arabic Relation Extraction using a Hybrid Semantic Knowledge Base - Machine Learning Approach |
| title_short | Exploiting Functional Discourse Grammar to Enhance Complex Arabic Relation Extraction using a Hybrid Semantic Knowledge Base - Machine Learning Approach |
| title_sort | Exploiting Functional Discourse Grammar to Enhance Complex Arabic Relation Extraction using a Hybrid Semantic Knowledge Base - Machine Learning Approach |
| topic | CCS Concepts: • Information systems → Information extraction; Additional Key Words and Phrases: Arabic relation extraction, Natural Language Processing, semantic web base, Functional Discourse Grammar, hybrid knowledge-based machine learning classification |
| url | https://bspace.buid.ac.ae/handle/1234/2795 https://doi.org/10.1145/361058 |