Named entity recognition in Turkish with Bayesian learning and hybrid approaches

Sermet Reha Yavuz; Dilek Küçük; Adnan Yazici

doi:10.1007/978-3-319-01604-7_13

Named entity recognition in Turkish with Bayesian learning and hybrid approaches

Sermet Reha Yavuz, Dilek Küçük, Adnan Yazici

Department of Electrical and Computer Engineering

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

3 Citations (Scopus)

Abstract

Named entity recognition is one of the significant textual information extraction tasks. In this paper, we present two approaches for named entity recognition on Turkish texts. The first is a Bayesian learning approach which is trained on a considerably limited training set. The second approach comprises two hybrid systems based on joint utilization of this Bayesian learning approach and a previously proposed rule-based named entity recognizer. All of the proposed three approaches achieve promising performance rates. This paper is significant as it reports the first use of the Bayesian approach for the task of named entity recognition on Turkish texts for which especially practical approaches are still insufficient.

Original language	English
Title of host publication	Information Sciences and Systems 2013 - Proceedings of the 28th International Symposium on Computer and Information Sciences
Publisher	Springer Verlag
Pages	129-138
Number of pages	10
ISBN (Print)	9783319016030
DOIs	https://doi.org/10.1007/978-3-319-01604-7_13
Publication status	Published - 2014
Event	28th International Symposium on Computer and Information Sciences, ISCIS 2013 - Paris, France Duration: Oct 28 2013 → Oct 29 2013

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	264 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	28th International Symposium on Computer and Information Sciences, ISCIS 2013
Country/Territory	France
City	Paris
Period	10/28/13 → 10/29/13

ASJC Scopus subject areas

Industrial and Manufacturing Engineering

Access to Document

10.1007/978-3-319-01604-7_13

Cite this

Yavuz, S. R., Küçük, D., & Yazici, A. (2014). Named entity recognition in Turkish with Bayesian learning and hybrid approaches. In Information Sciences and Systems 2013 - Proceedings of the 28th International Symposium on Computer and Information Sciences (pp. 129-138). (Lecture Notes in Electrical Engineering; Vol. 264 LNEE). Springer Verlag. https://doi.org/10.1007/978-3-319-01604-7_13

Named entity recognition in Turkish with Bayesian learning and hybrid approaches. / Yavuz, Sermet Reha; Küçük, Dilek; Yazici, Adnan.
Information Sciences and Systems 2013 - Proceedings of the 28th International Symposium on Computer and Information Sciences. Springer Verlag, 2014. p. 129-138 (Lecture Notes in Electrical Engineering; Vol. 264 LNEE).

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

Yavuz, SR, Küçük, D & Yazici, A 2014, Named entity recognition in Turkish with Bayesian learning and hybrid approaches. in Information Sciences and Systems 2013 - Proceedings of the 28th International Symposium on Computer and Information Sciences. Lecture Notes in Electrical Engineering, vol. 264 LNEE, Springer Verlag, pp. 129-138, 28th International Symposium on Computer and Information Sciences, ISCIS 2013, Paris, France, 10/28/13. https://doi.org/10.1007/978-3-319-01604-7_13

@inproceedings{1d829e3ca7b7434cb5884ff9fb1debbb,

title = "Named entity recognition in Turkish with Bayesian learning and hybrid approaches",

abstract = "Named entity recognition is one of the significant textual information extraction tasks. In this paper, we present two approaches for named entity recognition on Turkish texts. The first is a Bayesian learning approach which is trained on a considerably limited training set. The second approach comprises two hybrid systems based on joint utilization of this Bayesian learning approach and a previously proposed rule-based named entity recognizer. All of the proposed three approaches achieve promising performance rates. This paper is significant as it reports the first use of the Bayesian approach for the task of named entity recognition on Turkish texts for which especially practical approaches are still insufficient.",

author = "Yavuz, {Sermet Reha} and Dilek K{\"u}{\c c}{\"u}k and Adnan Yazici",

year = "2014",

doi = "10.1007/978-3-319-01604-7_13",

language = "English",

isbn = "9783319016030",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Verlag",

pages = "129--138",

booktitle = "Information Sciences and Systems 2013 - Proceedings of the 28th International Symposium on Computer and Information Sciences",

address = "Germany",

note = "28th International Symposium on Computer and Information Sciences, ISCIS 2013 ; Conference date: 28-10-2013 Through 29-10-2013",

}

TY - GEN

T1 - Named entity recognition in Turkish with Bayesian learning and hybrid approaches

AU - Yavuz, Sermet Reha

AU - Küçük, Dilek

AU - Yazici, Adnan

PY - 2014

Y1 - 2014

N2 - Named entity recognition is one of the significant textual information extraction tasks. In this paper, we present two approaches for named entity recognition on Turkish texts. The first is a Bayesian learning approach which is trained on a considerably limited training set. The second approach comprises two hybrid systems based on joint utilization of this Bayesian learning approach and a previously proposed rule-based named entity recognizer. All of the proposed three approaches achieve promising performance rates. This paper is significant as it reports the first use of the Bayesian approach for the task of named entity recognition on Turkish texts for which especially practical approaches are still insufficient.

AB - Named entity recognition is one of the significant textual information extraction tasks. In this paper, we present two approaches for named entity recognition on Turkish texts. The first is a Bayesian learning approach which is trained on a considerably limited training set. The second approach comprises two hybrid systems based on joint utilization of this Bayesian learning approach and a previously proposed rule-based named entity recognizer. All of the proposed three approaches achieve promising performance rates. This paper is significant as it reports the first use of the Bayesian approach for the task of named entity recognition on Turkish texts for which especially practical approaches are still insufficient.

UR - http://www.scopus.com/inward/record.url?scp=84899707742&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899707742&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-01604-7_13

DO - 10.1007/978-3-319-01604-7_13

M3 - Conference contribution

AN - SCOPUS:84899707742

SN - 9783319016030

T3 - Lecture Notes in Electrical Engineering

SP - 129

EP - 138

BT - Information Sciences and Systems 2013 - Proceedings of the 28th International Symposium on Computer and Information Sciences

PB - Springer Verlag

T2 - 28th International Symposium on Computer and Information Sciences, ISCIS 2013

Y2 - 28 October 2013 through 29 October 2013

ER -

Named entity recognition in Turkish with Bayesian learning and hybrid approaches

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this