Initial explorations on using CRFs for turkish named entity recognition

Gökhan Akin Şseker; Güļsen Eryǐgit

Initial explorations on using CRFs for turkish named entity recognition

Gökhan Akin Şseker^*, Güļsen Eryǐgit

^*Corresponding author for this work

Department of Artificial Intelligence and Data Engineering

Istanbul Technical University

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

53 Citations (Scopus)

Abstract

This paper reports the highest results (95% in MUC and 92% in CoNLL metric) in the literature for Turkish named entity recognition; more specifically for the task of detecting person, location and organization entities in general news texts. We give an in depth analysis of the previous reported results and make comparisons with them whenever possible. We use conditional random fields (CRFs) as our statistical model. The paper presents initial explorations on the usage of rich morphological structure of the Turkish language as features to CRFs together with the use of some basic and generative gazetteers.

Original language	English
Pages	2459-2474
Number of pages	16
Publication status	Published - 2012
Event	24th International Conference on Computational Linguistics, COLING 2012 - Mumbai, India Duration: 8 Dec 2012 → 15 Dec 2012

Conference

Conference	24th International Conference on Computational Linguistics, COLING 2012
Country/Territory	India
City	Mumbai
Period	8/12/12 → 15/12/12

Keywords

Conditional random fields
ENAMEX
Named entity recognition
Turkish

Cite this

@conference{797e851ddb4544c78c2a56fac7eafbe1,

title = "Initial explorations on using CRFs for turkish named entity recognition",

abstract = "This paper reports the highest results (95% in MUC and 92% in CoNLL metric) in the literature for Turkish named entity recognition; more specifically for the task of detecting person, location and organization entities in general news texts. We give an in depth analysis of the previous reported results and make comparisons with them whenever possible. We use conditional random fields (CRFs) as our statistical model. The paper presents initial explorations on the usage of rich morphological structure of the Turkish language as features to CRFs together with the use of some basic and generative gazetteers.",

keywords = "Conditional random fields, ENAMEX, Named entity recognition, Turkish",

author = "{\c S}seker, {G{\"o}khan Akin} and G{\"u}ļsen Eryǐgit",

year = "2012",

language = "English",

pages = "2459--2474",

note = "24th International Conference on Computational Linguistics, COLING 2012 ; Conference date: 08-12-2012 Through 15-12-2012",

}

TY - CONF

T1 - Initial explorations on using CRFs for turkish named entity recognition

AU - Şseker, Gökhan Akin

AU - Eryǐgit, Güļsen

PY - 2012

Y1 - 2012

N2 - This paper reports the highest results (95% in MUC and 92% in CoNLL metric) in the literature for Turkish named entity recognition; more specifically for the task of detecting person, location and organization entities in general news texts. We give an in depth analysis of the previous reported results and make comparisons with them whenever possible. We use conditional random fields (CRFs) as our statistical model. The paper presents initial explorations on the usage of rich morphological structure of the Turkish language as features to CRFs together with the use of some basic and generative gazetteers.

AB - This paper reports the highest results (95% in MUC and 92% in CoNLL metric) in the literature for Turkish named entity recognition; more specifically for the task of detecting person, location and organization entities in general news texts. We give an in depth analysis of the previous reported results and make comparisons with them whenever possible. We use conditional random fields (CRFs) as our statistical model. The paper presents initial explorations on the usage of rich morphological structure of the Turkish language as features to CRFs together with the use of some basic and generative gazetteers.

KW - Conditional random fields

KW - ENAMEX

KW - Named entity recognition

KW - Turkish

UR - http://www.scopus.com/inward/record.url?scp=84876812658&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84876812658

SP - 2459

EP - 2474

T2 - 24th International Conference on Computational Linguistics, COLING 2012

Y2 - 8 December 2012 through 15 December 2012

ER -

Initial explorations on using CRFs for turkish named entity recognition

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this