Paraphrasing Arabiuc Metaphor with Neural Machine Translation
The task of recognizing and generating paraphrases is an essential component in many Arabic natural language processing (NLP) applications. A well-established machine translation approach for automatically extracting paraphrases, leverages bilingual corpora to find the equivalent meaning of phrases...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://bspace.buid.ac.ae/handle/1234/3054 https://doi.org/10.1016/j.procs.2018.10.493. |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1862980619355553792 |
|---|---|
| author | Alkhatib, Manar |
| author2 | Shaalan, Khaled |
| author2_role | author |
| author_facet | Alkhatib, Manar Shaalan, Khaled |
| author_role | author |
| dc.creator.none.fl_str_mv | Alkhatib, Manar Shaalan, Khaled |
| dc.date.none.fl_str_mv | 2018-11-17 2025-05-15T10:14:08Z 2025-05-15T10:14:08Z |
| dc.identifier.none.fl_str_mv | Alkhatib, M. and Shaalan, K. (2018) “Paraphrasing Arabic Metaphor with Neural Machine Translation,” Procedia Computer Science, 142, pp. 308–314. 1877-0509 https://bspace.buid.ac.ae/handle/1234/3054 https://doi.org/10.1016/j.procs.2018.10.493. |
| dc.language.none.fl_str_mv | en_US |
| dc.publisher.none.fl_str_mv | Elsevier |
| dc.relation.none.fl_str_mv | Procedia Computer Sciencev142 (2018): 308-314 |
| dc.subject.none.fl_str_mv | Neural Machine Translation; Paraphrasing; Metaphor; Arabic language |
| dc.title.none.fl_str_mv | Paraphrasing Arabiuc Metaphor with Neural Machine Translation |
| dc.type.none.fl_str_mv | Article |
| description | The task of recognizing and generating paraphrases is an essential component in many Arabic natural language processing (NLP) applications. A well-established machine translation approach for automatically extracting paraphrases, leverages bilingual corpora to find the equivalent meaning of phrases in a single language, is performed by "pivoting" over a shared translation in another language. Neural machine translation has recently become a viable alternative approach to the more widely-used statistical machine translation. In this paper, we revisit bilingual pivoting in the context of neural machine translation and present a paraphrasing model based mainly on neural networks. Our model describes paraphrases in a continuous space and generates candidate paraphrases for an Arabic source input. Experimental ntal results across datasets confirm that neural paraphrases significantly outperform those obtained with |
| id | budr_76fbc367b782debd1d152063008cc406 |
| identifier_str_mv | Alkhatib, M. and Shaalan, K. (2018) “Paraphrasing Arabic Metaphor with Neural Machine Translation,” Procedia Computer Science, 142, pp. 308–314. 1877-0509 |
| language_invalid_str_mv | en_US |
| network_acronym_str | budr |
| network_name_str | The British University in Dubai repository |
| oai_identifier_str | oai:bspace.buid.ac.ae:1234/3054 |
| publishDate | 2018 |
| publisher.none.fl_str_mv | Elsevier |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| spelling | Paraphrasing Arabiuc Metaphor with Neural Machine TranslationAlkhatib, ManarShaalan, KhaledNeural Machine Translation; Paraphrasing; Metaphor; Arabic languageThe task of recognizing and generating paraphrases is an essential component in many Arabic natural language processing (NLP) applications. A well-established machine translation approach for automatically extracting paraphrases, leverages bilingual corpora to find the equivalent meaning of phrases in a single language, is performed by "pivoting" over a shared translation in another language. Neural machine translation has recently become a viable alternative approach to the more widely-used statistical machine translation. In this paper, we revisit bilingual pivoting in the context of neural machine translation and present a paraphrasing model based mainly on neural networks. Our model describes paraphrases in a continuous space and generates candidate paraphrases for an Arabic source input. Experimental ntal results across datasets confirm that neural paraphrases significantly outperform those obtained withElsevier2025-05-15T10:14:08Z2025-05-15T10:14:08Z2018-11-17ArticleAlkhatib, M. and Shaalan, K. (2018) “Paraphrasing Arabic Metaphor with Neural Machine Translation,” Procedia Computer Science, 142, pp. 308–314.1877-0509https://bspace.buid.ac.ae/handle/1234/3054https://doi.org/10.1016/j.procs.2018.10.493.en_USProcedia Computer Sciencev142 (2018): 308-314oai:bspace.buid.ac.ae:1234/30542025-08-12T17:24:09Z |
| spellingShingle | Paraphrasing Arabiuc Metaphor with Neural Machine Translation Alkhatib, Manar Neural Machine Translation; Paraphrasing; Metaphor; Arabic language |
| title | Paraphrasing Arabiuc Metaphor with Neural Machine Translation |
| title_full | Paraphrasing Arabiuc Metaphor with Neural Machine Translation |
| title_fullStr | Paraphrasing Arabiuc Metaphor with Neural Machine Translation |
| title_full_unstemmed | Paraphrasing Arabiuc Metaphor with Neural Machine Translation |
| title_short | Paraphrasing Arabiuc Metaphor with Neural Machine Translation |
| title_sort | Paraphrasing Arabiuc Metaphor with Neural Machine Translation |
| topic | Neural Machine Translation; Paraphrasing; Metaphor; Arabic language |
| url | https://bspace.buid.ac.ae/handle/1234/3054 https://doi.org/10.1016/j.procs.2018.10.493. |