A Classifier to Distinguish between Cypriot Greek and Standard Modern Greek

Hanna Sababa; Athena Stassopoulou

doi:10.1109/SNAMS.2018.8554709

A Classifier to Distinguish between Cypriot Greek and Standard Modern Greek

Hanna Sababa, Athena Stassopoulou

Department of Computer Science

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

Abstract

The problem of discriminating between similar languages and dialects is one of the current challenges of natural language processing. In this paper, we describe the collection of a bidialectal corpus of Greek and the construction of a classifier to distinguish between Cypriot Greek (CG) and Standard Modern Greek (SMG). The corpus of CG and SMG was compiled from social media websites such as Facebook, Twitter and online forums. N-gram features were extracted and three classification algorithms were applied and tested on labeled sentences: multinomial naive Bayes (NB), linear support vector classifier (SVC) and logistic regression. All algorithms classified the test data with an accuracy of over 90%, with the multinomial NB classifier performing best, yielding a mean accuracy of 95%. This study adds to the existing body of work on the problem of discriminating between similar languages and is the first to examine CG and SMG. The results demonstrate the feasibility of an accurate Greek dialect classifier for academic or applied purposes.

Original language	English
Title of host publication	2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	251-255
Number of pages	5
ISBN (Electronic)	9781538695883
DOIs	https://doi.org/10.1109/SNAMS.2018.8554709
Publication status	Published - 30 Nov 2018
Event	5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018 - Valencia, Spain Duration: 15 Oct 2018 → 18 Oct 2018

Publication series

Name	2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018

Conference

Conference	5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018
Country/Territory	Spain
City	Valencia
Period	15/10/18 → 18/10/18

Keywords

feature extraction
machine learning
natural language processing
natural languages
statistical learning

Access to Document

10.1109/SNAMS.2018.8554709

Cite this

Sababa, H., & Stassopoulou, A. (2018). A Classifier to Distinguish between Cypriot Greek and Standard Modern Greek. In 2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018 (pp. 251-255). Article 8554709 (2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SNAMS.2018.8554709

Sababa, Hanna ; Stassopoulou, Athena. / A Classifier to Distinguish between Cypriot Greek and Standard Modern Greek. 2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 251-255 (2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018).

@inproceedings{ac8df0aaf2f149b88af20d7a3a2b219a,

title = "A Classifier to Distinguish between Cypriot Greek and Standard Modern Greek",

abstract = "The problem of discriminating between similar languages and dialects is one of the current challenges of natural language processing. In this paper, we describe the collection of a bidialectal corpus of Greek and the construction of a classifier to distinguish between Cypriot Greek (CG) and Standard Modern Greek (SMG). The corpus of CG and SMG was compiled from social media websites such as Facebook, Twitter and online forums. N-gram features were extracted and three classification algorithms were applied and tested on labeled sentences: multinomial naive Bayes (NB), linear support vector classifier (SVC) and logistic regression. All algorithms classified the test data with an accuracy of over 90%, with the multinomial NB classifier performing best, yielding a mean accuracy of 95%. This study adds to the existing body of work on the problem of discriminating between similar languages and is the first to examine CG and SMG. The results demonstrate the feasibility of an accurate Greek dialect classifier for academic or applied purposes.",

keywords = "feature extraction, machine learning, natural language processing, natural languages, statistical learning",

author = "Hanna Sababa and Athena Stassopoulou",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.; 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018 ; Conference date: 15-10-2018 Through 18-10-2018",

year = "2018",

month = nov,

day = "30",

doi = "10.1109/SNAMS.2018.8554709",

language = "English",

series = "2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "251--255",

booktitle = "2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018",

}

Sababa, H & Stassopoulou, A 2018, A Classifier to Distinguish between Cypriot Greek and Standard Modern Greek. in 2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018., 8554709, 2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018, Institute of Electrical and Electronics Engineers Inc., pp. 251-255, 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018, Valencia, Spain, 15/10/18. https://doi.org/10.1109/SNAMS.2018.8554709

A Classifier to Distinguish between Cypriot Greek and Standard Modern Greek. / Sababa, Hanna; Stassopoulou, Athena.
2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 251-255 8554709 (2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018).

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

TY - GEN

T1 - A Classifier to Distinguish between Cypriot Greek and Standard Modern Greek

AU - Sababa, Hanna

AU - Stassopoulou, Athena

PY - 2018/11/30

Y1 - 2018/11/30

N2 - The problem of discriminating between similar languages and dialects is one of the current challenges of natural language processing. In this paper, we describe the collection of a bidialectal corpus of Greek and the construction of a classifier to distinguish between Cypriot Greek (CG) and Standard Modern Greek (SMG). The corpus of CG and SMG was compiled from social media websites such as Facebook, Twitter and online forums. N-gram features were extracted and three classification algorithms were applied and tested on labeled sentences: multinomial naive Bayes (NB), linear support vector classifier (SVC) and logistic regression. All algorithms classified the test data with an accuracy of over 90%, with the multinomial NB classifier performing best, yielding a mean accuracy of 95%. This study adds to the existing body of work on the problem of discriminating between similar languages and is the first to examine CG and SMG. The results demonstrate the feasibility of an accurate Greek dialect classifier for academic or applied purposes.

AB - The problem of discriminating between similar languages and dialects is one of the current challenges of natural language processing. In this paper, we describe the collection of a bidialectal corpus of Greek and the construction of a classifier to distinguish between Cypriot Greek (CG) and Standard Modern Greek (SMG). The corpus of CG and SMG was compiled from social media websites such as Facebook, Twitter and online forums. N-gram features were extracted and three classification algorithms were applied and tested on labeled sentences: multinomial naive Bayes (NB), linear support vector classifier (SVC) and logistic regression. All algorithms classified the test data with an accuracy of over 90%, with the multinomial NB classifier performing best, yielding a mean accuracy of 95%. This study adds to the existing body of work on the problem of discriminating between similar languages and is the first to examine CG and SMG. The results demonstrate the feasibility of an accurate Greek dialect classifier for academic or applied purposes.

KW - feature extraction

KW - machine learning

KW - natural language processing

KW - natural languages

KW - statistical learning

UR - http://www.scopus.com/inward/record.url?scp=85060039196&partnerID=8YFLogxK

U2 - 10.1109/SNAMS.2018.8554709

DO - 10.1109/SNAMS.2018.8554709

M3 - Conference contribution

AN - SCOPUS:85060039196

T3 - 2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018

SP - 251

EP - 255

BT - 2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018

Y2 - 15 October 2018 through 18 October 2018

ER -

Sababa H, Stassopoulou A. A Classifier to Distinguish between Cypriot Greek and Standard Modern Greek. In 2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 251-255. 8554709. (2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018). doi: 10.1109/SNAMS.2018.8554709

A Classifier to Distinguish between Cypriot Greek and Standard Modern Greek

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this