Improved POS-tagging for Arabic by combining diverse taggers

Maytham Alabbas; Allan Ramsay

doi:10.1007/978-3-642-33409-2_12

Improved POS-tagging for Arabic by combining diverse taggers

Maytham Alabbas, Allan Ramsay

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

A number of POS-taggers for Arabic have been presented in the literature. These taggers are not in general 100% accurate, and any errors in tagging are likely to lead to errors in the next step of natural language processing. The current work shows an investigation of how the best taggers available today can be improved by combining them. Experimental results show that a very simple approach to combining taggers can lead to significant improvements over the best individual tagger. © 2012 IFIP International Federation for Information Processing.

Original language	English
Title of host publication	IFIP Advances in Information and Communication Technology\|IFIP Advances in Information and Communication Technology
Place of Publication	Berkin
Publisher	Springer Nature
Pages	107-116
Number of pages	9
Volume	381
ISBN (Print)	9783642334085
DOIs	https://doi.org/10.1007/978-3-642-33409-2_12
Publication status	Published - 2012
Event	8th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2012 - Halkidiki Duration: 1 Jul 2012 → … http://dx.doi.org/10.1007/978-3-642-33409-2_12

Publication series

Name	IFIP Advances in Information and Communication Technology,

Conference

Conference	8th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2012
City	Halkidiki
Period	1/07/12 → …
Internet address	http://dx.doi.org/10.1007/978-3-642-33409-2_12

Keywords

Arabic tagging
Combining systems

Access to Document

10.1007/978-3-642-33409-2_12

Cite this

@inproceedings{39f0d2e1866e4ce6a0f28ca941bd0e64,

title = "Improved POS-tagging for Arabic by combining diverse taggers",

abstract = "A number of POS-taggers for Arabic have been presented in the literature. These taggers are not in general 100% accurate, and any errors in tagging are likely to lead to errors in the next step of natural language processing. The current work shows an investigation of how the best taggers available today can be improved by combining them. Experimental results show that a very simple approach to combining taggers can lead to significant improvements over the best individual tagger. {\textcopyright} 2012 IFIP International Federation for Information Processing.",

keywords = "Arabic tagging, Combining systems",

author = "Maytham Alabbas and Allan Ramsay",

year = "2012",

doi = "10.1007/978-3-642-33409-2_12",

language = "English",

isbn = "9783642334085",

volume = "381",

series = "IFIP Advances in Information and Communication Technology,",

publisher = "Springer Nature",

pages = "107--116",

booktitle = "IFIP Advances in Information and Communication Technology|IFIP Advances in Information and Communication Technology",

address = "United States",

note = "8th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2012 ; Conference date: 01-07-2012",

url = "http://dx.doi.org/10.1007/978-3-642-33409-2_12",

}

Alabbas, M & Ramsay, A 2012, Improved POS-tagging for Arabic by combining diverse taggers. in IFIP Advances in Information and Communication Technology|IFIP Advances in Information and Communication Technology. vol. 381, IFIP Advances in Information and Communication Technology, Springer Nature, Berkin, pp. 107-116, 8th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2012, Halkidiki, 1/07/12. https://doi.org/10.1007/978-3-642-33409-2_12

Improved POS-tagging for Arabic by combining diverse taggers. / Alabbas, Maytham; Ramsay, Allan.
IFIP Advances in Information and Communication Technology|IFIP Advances in Information and Communication Technology. Vol. 381 Berkin: Springer Nature, 2012. p. 107-116 (IFIP Advances in Information and Communication Technology,).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Improved POS-tagging for Arabic by combining diverse taggers

AU - Alabbas, Maytham

AU - Ramsay, Allan

PY - 2012

Y1 - 2012

N2 - A number of POS-taggers for Arabic have been presented in the literature. These taggers are not in general 100% accurate, and any errors in tagging are likely to lead to errors in the next step of natural language processing. The current work shows an investigation of how the best taggers available today can be improved by combining them. Experimental results show that a very simple approach to combining taggers can lead to significant improvements over the best individual tagger. © 2012 IFIP International Federation for Information Processing.

AB - A number of POS-taggers for Arabic have been presented in the literature. These taggers are not in general 100% accurate, and any errors in tagging are likely to lead to errors in the next step of natural language processing. The current work shows an investigation of how the best taggers available today can be improved by combining them. Experimental results show that a very simple approach to combining taggers can lead to significant improvements over the best individual tagger. © 2012 IFIP International Federation for Information Processing.

KW - Arabic tagging

KW - Combining systems

U2 - 10.1007/978-3-642-33409-2_12

DO - 10.1007/978-3-642-33409-2_12

M3 - Conference contribution

SN - 9783642334085

VL - 381

T3 - IFIP Advances in Information and Communication Technology,

SP - 107

EP - 116

BT - IFIP Advances in Information and Communication Technology|IFIP Advances in Information and Communication Technology

PB - Springer Nature

CY - Berkin

T2 - 8th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2012

Y2 - 1 July 2012

ER -

Improved POS-tagging for Arabic by combining diverse taggers

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this