A single-model approach for Arabic segmentation, POS tagging, and named entity recognition

Abed Alhakim Freihat; Gabor Bella; Hamdy Mubarak; Fausto Giunchiglia

doi:10.1109/ICNLSP.2018.8374393

A single-model approach for Arabic segmentation, POS tagging, and named entity recognition

Abed Alhakim Freihat, Gabor Bella, Hamdy Mubarak, Fausto Giunchiglia

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

4 Citations (Scopus)

Abstract

This paper presents an entirely new, one-million-word annotated corpus for a comprehensive, machine-learning-based preprocessing of text in Modern Standard Arabic. Contrary to the conventional pipeline architecture, we solve the NLP tasks of word segmentation, POS tagging and named entity recognition as a single sequence labeling task. This single-component configuration results in a faster operation and is able to provide state-of-the-art precision and recall according to our evaluations. The fine-grained output tag set output by our annotator greatly simplifies downstream tasks such as lemmatization. Provided as a trained OpenNLP component, the annotator is free for research purposes.

Original language	English
Title of host publication	2nd International Conference on Natural Language and Speech Processing, ICNLSP 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-8
Number of pages	8
ISBN (Electronic)	9781538645437
DOIs	https://doi.org/10.1109/ICNLSP.2018.8374393
Publication status	Published - 6 Jun 2018
Event	2nd International Conference on Natural Language and Speech Processing, ICNLSP 2018 - Algiers, Algeria Duration: 25 Apr 2018 → 26 Apr 2018

Other

Other	2nd International Conference on Natural Language and Speech Processing, ICNLSP 2018
Country	Algeria
City	Algiers
Period	25/4/18 → 26/4/18

Fingerprint

Keywords

Lemmatization
Machine learning
Named entity recognition
NLP
POS tagging
Segmentation

ASJC Scopus subject areas

Linguistics and Language
Communication
Artificial Intelligence
Signal Processing

Cite this

Freihat, A. A., Bella, G., Mubarak, H., & Giunchiglia, F. (2018). A single-model approach for Arabic segmentation, POS tagging, and named entity recognition. In 2nd International Conference on Natural Language and Speech Processing, ICNLSP 2018 (pp. 1-8). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICNLSP.2018.8374393

A single-model approach for Arabic segmentation, POS tagging, and named entity recognition. / Freihat, Abed Alhakim; Bella, Gabor; Mubarak, Hamdy; Giunchiglia, Fausto.

2nd International Conference on Natural Language and Speech Processing, ICNLSP 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-8.

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

Freihat, AA, Bella, G, Mubarak, H & Giunchiglia, F 2018, A single-model approach for Arabic segmentation, POS tagging, and named entity recognition. in 2nd International Conference on Natural Language and Speech Processing, ICNLSP 2018. Institute of Electrical and Electronics Engineers Inc., pp. 1-8, 2nd International Conference on Natural Language and Speech Processing, ICNLSP 2018, Algiers, Algeria, 25/4/18. https://doi.org/10.1109/ICNLSP.2018.8374393

@inproceedings{c9420bf11e654d6ea29d0a274c3e738e,

title = "A single-model approach for Arabic segmentation, POS tagging, and named entity recognition",

abstract = "This paper presents an entirely new, one-million-word annotated corpus for a comprehensive, machine-learning-based preprocessing of text in Modern Standard Arabic. Contrary to the conventional pipeline architecture, we solve the NLP tasks of word segmentation, POS tagging and named entity recognition as a single sequence labeling task. This single-component configuration results in a faster operation and is able to provide state-of-the-art precision and recall according to our evaluations. The fine-grained output tag set output by our annotator greatly simplifies downstream tasks such as lemmatization. Provided as a trained OpenNLP component, the annotator is free for research purposes.",

keywords = "Lemmatization, Machine learning, Named entity recognition, NLP, POS tagging, Segmentation",

author = "Freihat, {Abed Alhakim} and Gabor Bella and Hamdy Mubarak and Fausto Giunchiglia",

year = "2018",

month = jun

day = "6",

doi = "10.1109/ICNLSP.2018.8374393",

language = "English",

pages = "1--8",

booktitle = "2nd International Conference on Natural Language and Speech Processing, ICNLSP 2018",

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

note = "2nd International Conference on Natural Language and Speech Processing, ICNLSP 2018 ; Conference date: 25-04-2018 Through 26-04-2018",

}

TY - GEN

T1 - A single-model approach for Arabic segmentation, POS tagging, and named entity recognition

AU - Freihat, Abed Alhakim

AU - Bella, Gabor

AU - Mubarak, Hamdy

AU - Giunchiglia, Fausto

PY - 2018/6/6

Y1 - 2018/6/6

N2 - This paper presents an entirely new, one-million-word annotated corpus for a comprehensive, machine-learning-based preprocessing of text in Modern Standard Arabic. Contrary to the conventional pipeline architecture, we solve the NLP tasks of word segmentation, POS tagging and named entity recognition as a single sequence labeling task. This single-component configuration results in a faster operation and is able to provide state-of-the-art precision and recall according to our evaluations. The fine-grained output tag set output by our annotator greatly simplifies downstream tasks such as lemmatization. Provided as a trained OpenNLP component, the annotator is free for research purposes.

AB - This paper presents an entirely new, one-million-word annotated corpus for a comprehensive, machine-learning-based preprocessing of text in Modern Standard Arabic. Contrary to the conventional pipeline architecture, we solve the NLP tasks of word segmentation, POS tagging and named entity recognition as a single sequence labeling task. This single-component configuration results in a faster operation and is able to provide state-of-the-art precision and recall according to our evaluations. The fine-grained output tag set output by our annotator greatly simplifies downstream tasks such as lemmatization. Provided as a trained OpenNLP component, the annotator is free for research purposes.

KW - Lemmatization

KW - Machine learning

KW - Named entity recognition

KW - NLP

KW - POS tagging

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85049371695&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049371695&partnerID=8YFLogxK

U2 - 10.1109/ICNLSP.2018.8374393

DO - 10.1109/ICNLSP.2018.8374393

M3 - Conference contribution

AN - SCOPUS:85049371695

SP - 1

EP - 8

BT - 2nd International Conference on Natural Language and Speech Processing, ICNLSP 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Conference on Natural Language and Speech Processing, ICNLSP 2018

Y2 - 25 April 2018 through 26 April 2018

ER -

Access to Document

10.1109/ICNLSP.2018.8374393