Building machine-readable knowledge representations for Turkish sign language generation

Cihat Eryiğit; Hatice Köse; Meltem Kelepir; Gülşen Eryiğit

doi:10.1016/j.knosys.2016.04.014

Building machine-readable knowledge representations for Turkish sign language generation

Cihat Eryiğit, Hatice Köse, Meltem Kelepir, Gülşen Eryiğit^*

^*Corresponding author for this work

Department of Artificial Intelligence and Data Engineering

Research output: Contribution to journal › Article › peer-review

12 Citations (Scopus)

Abstract

This article proposes a representation scheme for depicting the Turkish Sign Language (TİD) electronically for use in an automated machine translation system whose basic aim is to translate the Turkish primary school educational materials to TİD. The main contribution of the article is the introduction of a machine-readable knowledge representation for TİD for the first time in the literature. Like many resource-poor languages, TİD lacks electronic language resources usable in computerized systems. The utilization of the proposed scheme for resource creation is also provided in this article by two means: an interactive online dictionary platform for TİD and an ELAN add-on for corpus creation.

Original language	English
Pages (from-to)	179-194
Number of pages	16
Journal	Knowledge-Based Systems
Volume	108
DOIs	https://doi.org/10.1016/j.knosys.2016.04.014
Publication status	Published - 15 Sept 2016

Bibliographical note

Publisher Copyright:
© 2016

Funding

This research is supported under the project “A Signing Avatar System for Turkish to Turkish Sign Language Machine Translation” by The Scientific and Technological Research Council of Turkey (TUBITAK) with a 1003 grant (no: 114E263). This research is supported under the project “A Signing Avatar System for Turkish to Turkish Sign Language Machine Translation” by The Scientific and Technological Research Council of Turkey (TUBITAK) with a 1003 grant (no: 114E263), and partly under the Project “Machine translation system for Turkish Sign Language,” by the Istanbul Technical University Research Foundation with a BAP grant (no: 37941). We are grateful for the support of our signers Jale Erdul, Elvan Tamyürek Özparlak and Nevzat Kırgıç, our students Serpil Karabüklü, Dilara Torunoğlu-Selamet and Aslı Özkul, and our Project advisor Prof. Dr. Sumru Özsoy. We also want to offer our special thanks to our three anonymous reviewers for insightful comments and suggestions that helped us improve the final version of the article.

Funders	Funder number
Istanbul Technical University Research Foundation	37941
TUBITAK	114E263
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu

Keywords

Machine-readable knowledge Representations
Sign language
Turkish sign language
TİD

Access to Document

10.1016/j.knosys.2016.04.014

Cite this

@article{07fcc49d27714d65a5847876eac90d42,

title = "Building machine-readable knowledge representations for Turkish sign language generation",

abstract = "This article proposes a representation scheme for depicting the Turkish Sign Language (TİD) electronically for use in an automated machine translation system whose basic aim is to translate the Turkish primary school educational materials to TİD. The main contribution of the article is the introduction of a machine-readable knowledge representation for TİD for the first time in the literature. Like many resource-poor languages, TİD lacks electronic language resources usable in computerized systems. The utilization of the proposed scheme for resource creation is also provided in this article by two means: an interactive online dictionary platform for TİD and an ELAN add-on for corpus creation.",

keywords = "Machine-readable knowledge Representations, Sign language, Turkish sign language, TİD",

author = "Cihat Eryiğit and Hatice K{\"o}se and Meltem Kelepir and G{\"u}l{\c s}en Eryiğit",

note = "Publisher Copyright: {\textcopyright} 2016",

year = "2016",

month = sep,

day = "15",

doi = "10.1016/j.knosys.2016.04.014",

language = "English",

volume = "108",

pages = "179--194",

journal = "Knowledge-Based Systems",

issn = "0950-7051",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Building machine-readable knowledge representations for Turkish sign language generation

AU - Eryiğit, Cihat

AU - Köse, Hatice

AU - Kelepir, Meltem

AU - Eryiğit, Gülşen

PY - 2016/9/15

Y1 - 2016/9/15

N2 - This article proposes a representation scheme for depicting the Turkish Sign Language (TİD) electronically for use in an automated machine translation system whose basic aim is to translate the Turkish primary school educational materials to TİD. The main contribution of the article is the introduction of a machine-readable knowledge representation for TİD for the first time in the literature. Like many resource-poor languages, TİD lacks electronic language resources usable in computerized systems. The utilization of the proposed scheme for resource creation is also provided in this article by two means: an interactive online dictionary platform for TİD and an ELAN add-on for corpus creation.

AB - This article proposes a representation scheme for depicting the Turkish Sign Language (TİD) electronically for use in an automated machine translation system whose basic aim is to translate the Turkish primary school educational materials to TİD. The main contribution of the article is the introduction of a machine-readable knowledge representation for TİD for the first time in the literature. Like many resource-poor languages, TİD lacks electronic language resources usable in computerized systems. The utilization of the proposed scheme for resource creation is also provided in this article by two means: an interactive online dictionary platform for TİD and an ELAN add-on for corpus creation.

KW - Machine-readable knowledge Representations

KW - Sign language

KW - Turkish sign language

KW - TİD

UR - http://www.scopus.com/inward/record.url?scp=84992307082&partnerID=8YFLogxK

U2 - 10.1016/j.knosys.2016.04.014

DO - 10.1016/j.knosys.2016.04.014

M3 - Article

AN - SCOPUS:84992307082

SN - 0950-7051

VL - 108

SP - 179

EP - 194

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

ER -

Building machine-readable knowledge representations for Turkish sign language generation

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this