Challenging language-Dependent segmentation for Arabic

An application to machine translation and part-of-Speech tagging

Hassan Sajjad, Fahim Dalvi, Nadir Durrani, Ahmed Abdelali, Yonatan Belinkov, Stephan Vogel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)
PublisherAssociation for Computational Linguistics (ACL)
Pages601-607
Number of pages7
Volume2
ISBN (Electronic)9781945626760
DOIs
Publication statusPublished - 1 Jan 2017
Event55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada
Duration: 30 Jul 20174 Aug 2017

Other

Other55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
CountryCanada
CityVancouver
Period30/7/174/8/17

Fingerprint

Convolution
Neural networks
language
dialect
neural network
performance
learning
segmentation
Language
Machine Translation
Segmentation
Part-of-speech Tagging
Tagging
Natural Language Processing
Word Segmentation
Machine Translation System
Subword
Data-driven
Performance Art
Neural Networks

ASJC Scopus subject areas

  • Language and Linguistics
  • Artificial Intelligence
  • Software
  • Linguistics and Language

Cite this

Sajjad, H., Dalvi, F., Durrani, N., Abdelali, A., Belinkov, Y., & Vogel, S. (2017). Challenging language-Dependent segmentation for Arabic: An application to machine translation and part-of-Speech tagging. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers) (Vol. 2, pp. 601-607). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/P17-2095

Challenging language-Dependent segmentation for Arabic : An application to machine translation and part-of-Speech tagging. / Sajjad, Hassan; Dalvi, Fahim; Durrani, Nadir; Abdelali, Ahmed; Belinkov, Yonatan; Vogel, Stephan.

ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Vol. 2 Association for Computational Linguistics (ACL), 2017. p. 601-607.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sajjad, H, Dalvi, F, Durrani, N, Abdelali, A, Belinkov, Y & Vogel, S 2017, Challenging language-Dependent segmentation for Arabic: An application to machine translation and part-of-Speech tagging. in ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). vol. 2, Association for Computational Linguistics (ACL), pp. 601-607, 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, 30/7/17. https://doi.org/10.18653/v1/P17-2095
Sajjad H, Dalvi F, Durrani N, Abdelali A, Belinkov Y, Vogel S. Challenging language-Dependent segmentation for Arabic: An application to machine translation and part-of-Speech tagging. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Vol. 2. Association for Computational Linguistics (ACL). 2017. p. 601-607 https://doi.org/10.18653/v1/P17-2095
Sajjad, Hassan ; Dalvi, Fahim ; Durrani, Nadir ; Abdelali, Ahmed ; Belinkov, Yonatan ; Vogel, Stephan. / Challenging language-Dependent segmentation for Arabic : An application to machine translation and part-of-Speech tagging. ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Vol. 2 Association for Computational Linguistics (ACL), 2017. pp. 601-607
@inproceedings{f9c0511867674022b9f0c0cc261385aa,
title = "Challenging language-Dependent segmentation for Arabic: An application to machine translation and part-of-Speech tagging",
abstract = "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.",
author = "Hassan Sajjad and Fahim Dalvi and Nadir Durrani and Ahmed Abdelali and Yonatan Belinkov and Stephan Vogel",
year = "2017",
month = "1",
day = "1",
doi = "10.18653/v1/P17-2095",
language = "English",
volume = "2",
pages = "601--607",
booktitle = "ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Challenging language-Dependent segmentation for Arabic

T2 - An application to machine translation and part-of-Speech tagging

AU - Sajjad, Hassan

AU - Dalvi, Fahim

AU - Durrani, Nadir

AU - Abdelali, Ahmed

AU - Belinkov, Yonatan

AU - Vogel, Stephan

PY - 2017/1/1

Y1 - 2017/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85040627430&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040627430&partnerID=8YFLogxK

U2 - 10.18653/v1/P17-2095

DO - 10.18653/v1/P17-2095

M3 - Conference contribution

VL - 2

SP - 601

EP - 607

BT - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)

PB - Association for Computational Linguistics (ACL)

ER -