Machine translation between Hebrew and Arabic: Needs, challenges and preliminary solutions

Reshef Shilon; Nizar Habash; Alon Lavie; Shuly Wintner

Machine translation between Hebrew and Arabic: Needs, challenges and preliminary solutions

Reshef Shilon, Nizar Habash, Alon Lavie, Shuly Wintner

Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

Hebrew and Arabic are related but mutually incomprehensible languages with complex morphology and scarce parallel corpora. Machine translation between the two languages is therefore interesting and challenging. We discuss similarities and differences between Hebrew and Arabic, the benefits and challenges that they induce, respectively, and their implications for machine translation. We highlight the shortcomings of using English as a pivot language and advocate a direct, transfer-based and linguisticallyinformed (but still statistical, and hence scalable) approach. We report preliminary results of such a system that we are currently developing.

Original language	English (US)
State	Published - 2010
Event	9th Biennial Conference of the Association for Machine Translation in the Americas, AMTA 2010 - Denver, CO, United States Duration: Oct 31 2010 → Nov 4 2010

Other

Other	9th Biennial Conference of the Association for Machine Translation in the Americas, AMTA 2010
Country/Territory	United States
City	Denver, CO
Period	10/31/10 → 11/4/10

ASJC Scopus subject areas

Language and Linguistics
Human-Computer Interaction
Software

Cite this

@conference{6ada3370a4ee4c69a71b0313cbbff6d0,

title = "Machine translation between Hebrew and Arabic: Needs, challenges and preliminary solutions",

abstract = "Hebrew and Arabic are related but mutually incomprehensible languages with complex morphology and scarce parallel corpora. Machine translation between the two languages is therefore interesting and challenging. We discuss similarities and differences between Hebrew and Arabic, the benefits and challenges that they induce, respectively, and their implications for machine translation. We highlight the shortcomings of using English as a pivot language and advocate a direct, transfer-based and linguisticallyinformed (but still statistical, and hence scalable) approach. We report preliminary results of such a system that we are currently developing.",

author = "Reshef Shilon and Nizar Habash and Alon Lavie and Shuly Wintner",

year = "2010",

language = "English (US)",

note = "9th Biennial Conference of the Association for Machine Translation in the Americas, AMTA 2010 ; Conference date: 31-10-2010 Through 04-11-2010",

}

TY - CONF

T1 - Machine translation between Hebrew and Arabic

T2 - 9th Biennial Conference of the Association for Machine Translation in the Americas, AMTA 2010

AU - Shilon, Reshef

AU - Habash, Nizar

AU - Lavie, Alon

AU - Wintner, Shuly

PY - 2010

Y1 - 2010

N2 - Hebrew and Arabic are related but mutually incomprehensible languages with complex morphology and scarce parallel corpora. Machine translation between the two languages is therefore interesting and challenging. We discuss similarities and differences between Hebrew and Arabic, the benefits and challenges that they induce, respectively, and their implications for machine translation. We highlight the shortcomings of using English as a pivot language and advocate a direct, transfer-based and linguisticallyinformed (but still statistical, and hence scalable) approach. We report preliminary results of such a system that we are currently developing.

AB - Hebrew and Arabic are related but mutually incomprehensible languages with complex morphology and scarce parallel corpora. Machine translation between the two languages is therefore interesting and challenging. We discuss similarities and differences between Hebrew and Arabic, the benefits and challenges that they induce, respectively, and their implications for machine translation. We highlight the shortcomings of using English as a pivot language and advocate a direct, transfer-based and linguisticallyinformed (but still statistical, and hence scalable) approach. We report preliminary results of such a system that we are currently developing.

UR - http://www.scopus.com/inward/record.url?scp=84857565724&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857565724&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84857565724

Y2 - 31 October 2010 through 4 November 2010

ER -

Machine translation between Hebrew and Arabic: Needs, challenges and preliminary solutions

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this