Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging

<p dir="ltr">Word segmentation plays a pivotal role in improving any Arabic NLP application. Therefore, a lot of research has been spent in improving its accuracy. Off-the-shelf tools, however, are: i) complicated to use and ii) domain/dialect dependent. We explore three language-ind...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Hassan Sajjad (5297441) (author)
مؤلفون آخرون: Fahim Dalvi (18427905) (author), Nadir Durrani (5297438) (author), Ahmed Abdelali (19691659) (author), Yonatan Belinkov (18973897) (author), Stephan Vogel (19691698) (author)
منشور في: 2017
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513557097349120
author Hassan Sajjad (5297441)
author2 Fahim Dalvi (18427905)
Nadir Durrani (5297438)
Ahmed Abdelali (19691659)
Yonatan Belinkov (18973897)
Stephan Vogel (19691698)
author2_role author
author
author
author
author
author_facet Hassan Sajjad (5297441)
Fahim Dalvi (18427905)
Nadir Durrani (5297438)
Ahmed Abdelali (19691659)
Yonatan Belinkov (18973897)
Stephan Vogel (19691698)
author_role author
dc.creator.none.fl_str_mv Hassan Sajjad (5297441)
Fahim Dalvi (18427905)
Nadir Durrani (5297438)
Ahmed Abdelali (19691659)
Yonatan Belinkov (18973897)
Stephan Vogel (19691698)
dc.date.none.fl_str_mv 2017-07-30T06:00:00Z
dc.identifier.none.fl_str_mv 10.18653/v1/p17-2095
dc.relation.none.fl_str_mv https://figshare.com/articles/conference_contribution/Challenging_Language-Dependent_Segmentation_for_Arabic_An__Application_to_Machine_Translation_and_Part-of-Speech_Tagging/27050737
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Language, communication and culture
Linguistics
Word Segmentation
Arabic NLP
Morphological Segmentation
Accuracy Improvement
Off-the-Shelf Tools
Domain Dependency
Dialect Dependency
dc.title.none.fl_str_mv Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging
dc.type.none.fl_str_mv Text
Conference contribution
info:eu-repo/semantics/publishedVersion
text
conference object
description <p dir="ltr">Word segmentation plays a pivotal role in improving any Arabic NLP application. Therefore, a lot of research has been spent in improving its accuracy. Off-the-shelf tools, however, are: i) complicated to use and ii) domain/dialect dependent. We explore three language-independent alternatives to morphological segmentation using: i) data-driven sub-word units, ii) characters as a unit of learning, and iii) word embeddings learned using a character CNN (Convolution Neural Network). On the tasks of Machine Translation and POS tagging, we found these methods to achieve close to, and occasionally surpass state-of-the-art performance. In our analysis, we show that a neural machine translation system is sensitive to the ratio of source and target tokens, and a ratio close to 1 or greater, gives optimal performance.</p><h2>Other Information</h2><p dir="ltr">Published in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See conference contribution on publisher's website: <a href="https://dx.doi.org/10.18653/v1/p17-2095" target="_blank">https://dx.doi.org/10.18653/v1/p17-2095</a></p><p dir="ltr">Conference information: 55th Annual Meeting of the Association for Computational Linguistics (Short Papers), pages 518–523 Vancouver, Canada, July 30 - August 4, 2017</p>
eu_rights_str_mv openAccess
id Manara2_ab19b804bae19ef57dbc15c1615860c8
identifier_str_mv 10.18653/v1/p17-2095
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/27050737
publishDate 2017
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech TaggingHassan Sajjad (5297441)Fahim Dalvi (18427905)Nadir Durrani (5297438)Ahmed Abdelali (19691659)Yonatan Belinkov (18973897)Stephan Vogel (19691698)Information and computing sciencesArtificial intelligenceLanguage, communication and cultureLinguisticsWord SegmentationArabic NLPMorphological SegmentationAccuracy ImprovementOff-the-Shelf ToolsDomain DependencyDialect Dependency<p dir="ltr">Word segmentation plays a pivotal role in improving any Arabic NLP application. Therefore, a lot of research has been spent in improving its accuracy. Off-the-shelf tools, however, are: i) complicated to use and ii) domain/dialect dependent. We explore three language-independent alternatives to morphological segmentation using: i) data-driven sub-word units, ii) characters as a unit of learning, and iii) word embeddings learned using a character CNN (Convolution Neural Network). On the tasks of Machine Translation and POS tagging, we found these methods to achieve close to, and occasionally surpass state-of-the-art performance. In our analysis, we show that a neural machine translation system is sensitive to the ratio of source and target tokens, and a ratio close to 1 or greater, gives optimal performance.</p><h2>Other Information</h2><p dir="ltr">Published in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See conference contribution on publisher's website: <a href="https://dx.doi.org/10.18653/v1/p17-2095" target="_blank">https://dx.doi.org/10.18653/v1/p17-2095</a></p><p dir="ltr">Conference information: 55th Annual Meeting of the Association for Computational Linguistics (Short Papers), pages 518–523 Vancouver, Canada, July 30 - August 4, 2017</p>2017-07-30T06:00:00ZTextConference contributioninfo:eu-repo/semantics/publishedVersiontextconference object10.18653/v1/p17-2095https://figshare.com/articles/conference_contribution/Challenging_Language-Dependent_Segmentation_for_Arabic_An__Application_to_Machine_Translation_and_Part-of-Speech_Tagging/27050737CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/270507372017-07-30T06:00:00Z
spellingShingle Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging
Hassan Sajjad (5297441)
Information and computing sciences
Artificial intelligence
Language, communication and culture
Linguistics
Word Segmentation
Arabic NLP
Morphological Segmentation
Accuracy Improvement
Off-the-Shelf Tools
Domain Dependency
Dialect Dependency
status_str publishedVersion
title Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging
title_full Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging
title_fullStr Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging
title_full_unstemmed Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging
title_short Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging
title_sort Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging
topic Information and computing sciences
Artificial intelligence
Language, communication and culture
Linguistics
Word Segmentation
Arabic NLP
Morphological Segmentation
Accuracy Improvement
Off-the-Shelf Tools
Domain Dependency
Dialect Dependency