AKEA: An Arabic keyphrase extraction algorithm

Eslam Amer; Khaled Foad

doi:10.1007/978-3-319-48308-5_14

AKEA: An Arabic keyphrase extraction algorithm

Eslam Amer^*, Khaled Foad

^*Corresponding author for this work

School of Computing

Benha University

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

Abstract

Keyphrase extraction is a critical step in many natural language processing and Information retrieval applications. In this paper, we introduce AKEA, a keyphrase extraction algorithm for single Arabic documents. AKEA is an unsupervised algorithm as it does not need any type of training in order to achieve its task. We rely on heuristics that collaborate linguistic patterns based on Part-Of-Speech (POS) tags, statistical knowledge, and the internal structural pattern of terms (i.e. word-occurrence). We employ the usage of Arabic Wikipedia to improve the ranking (or significance) of candidate keyphrases by adding a confidence score if the candidate exist as an indexed Wikipedia concept. Experimental results show that on average AKEA has the highest precision value, the highest F-measure value which indicates it presents more accurate results compared to its other algorithms.

Original language	English
Title of host publication	Proceedings of the International Conference on Advanced Intelligent Systems and Informatics, 2016
Editors	Aboul Ella Hassanien, Khaled Shaalan, Ahmad Taher Azar, Tarek Gaber, Mohamed F. Tolba
Publisher	Springer
Pages	137-146
Number of pages	10
ISBN (Electronic)	9783319483085
ISBN (Print)	9783319483078
DOIs	https://doi.org/10.1007/978-3-319-48308-5_14
Publication status	Published - 18 Oct 2016
Event	2nd International Conference on Advanced Intelligent Systems and Informatics, AISI 2016 - Cairo, Egypt Duration: 24 Oct 2016 → 26 Oct 2016

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	533
ISSN (Print)	2194-5357

Conference

Conference	2nd International Conference on Advanced Intelligent Systems and Informatics, AISI 2016
Country/Territory	Egypt
City	Cairo
Period	24/10/16 → 26/10/16

Keywords

Keyphrase extraction
Natural language processing

Access to Document

10.1007/978-3-319-48308-5_14

Cite this

Amer, E., & Foad, K. (2016). AKEA: An Arabic keyphrase extraction algorithm. In A. E. Hassanien, K. Shaalan, A. T. Azar, T. Gaber, & M. F. Tolba (Eds.), Proceedings of the International Conference on Advanced Intelligent Systems and Informatics, 2016 (pp. 137-146). (Advances in Intelligent Systems and Computing; Vol. 533). Springer. https://doi.org/10.1007/978-3-319-48308-5_14

@inproceedings{d0f43638808b4263af5109cd4e8973b2,

title = "AKEA: An Arabic keyphrase extraction algorithm",

abstract = "Keyphrase extraction is a critical step in many natural language processing and Information retrieval applications. In this paper, we introduce AKEA, a keyphrase extraction algorithm for single Arabic documents. AKEA is an unsupervised algorithm as it does not need any type of training in order to achieve its task. We rely on heuristics that collaborate linguistic patterns based on Part-Of-Speech (POS) tags, statistical knowledge, and the internal structural pattern of terms (i.e. word-occurrence). We employ the usage of Arabic Wikipedia to improve the ranking (or significance) of candidate keyphrases by adding a confidence score if the candidate exist as an indexed Wikipedia concept. Experimental results show that on average AKEA has the highest precision value, the highest F-measure value which indicates it presents more accurate results compared to its other algorithms.",

keywords = "Keyphrase extraction, Natural language processing",

author = "Eslam Amer and Khaled Foad",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2017.; 2nd International Conference on Advanced Intelligent Systems and Informatics, AISI 2016 ; Conference date: 24-10-2016 Through 26-10-2016",

year = "2016",

month = oct,

day = "18",

doi = "10.1007/978-3-319-48308-5_14",

language = "English",

isbn = "9783319483078",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer",

pages = "137--146",

editor = "Hassanien, {Aboul Ella} and Khaled Shaalan and Azar, {Ahmad Taher} and Tarek Gaber and Tolba, {Mohamed F.}",

booktitle = "Proceedings of the International Conference on Advanced Intelligent Systems and Informatics, 2016",

}

Amer, E & Foad, K 2016, AKEA: An Arabic keyphrase extraction algorithm. in AE Hassanien, K Shaalan, AT Azar, T Gaber & MF Tolba (eds), Proceedings of the International Conference on Advanced Intelligent Systems and Informatics, 2016. Advances in Intelligent Systems and Computing, vol. 533, Springer, pp. 137-146, 2nd International Conference on Advanced Intelligent Systems and Informatics, AISI 2016, Cairo, Egypt, 24/10/16. https://doi.org/10.1007/978-3-319-48308-5_14

AKEA: An Arabic keyphrase extraction algorithm. / Amer, Eslam; Foad, Khaled.
Proceedings of the International Conference on Advanced Intelligent Systems and Informatics, 2016. ed. / Aboul Ella Hassanien; Khaled Shaalan; Ahmad Taher Azar; Tarek Gaber; Mohamed F. Tolba. Springer, 2016. p. 137-146 (Advances in Intelligent Systems and Computing; Vol. 533).

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

TY - GEN

T1 - AKEA

T2 - 2nd International Conference on Advanced Intelligent Systems and Informatics, AISI 2016

AU - Amer, Eslam

AU - Foad, Khaled

N1 - Publisher Copyright: © Springer International Publishing AG 2017.

PY - 2016/10/18

Y1 - 2016/10/18

N2 - Keyphrase extraction is a critical step in many natural language processing and Information retrieval applications. In this paper, we introduce AKEA, a keyphrase extraction algorithm for single Arabic documents. AKEA is an unsupervised algorithm as it does not need any type of training in order to achieve its task. We rely on heuristics that collaborate linguistic patterns based on Part-Of-Speech (POS) tags, statistical knowledge, and the internal structural pattern of terms (i.e. word-occurrence). We employ the usage of Arabic Wikipedia to improve the ranking (or significance) of candidate keyphrases by adding a confidence score if the candidate exist as an indexed Wikipedia concept. Experimental results show that on average AKEA has the highest precision value, the highest F-measure value which indicates it presents more accurate results compared to its other algorithms.

AB - Keyphrase extraction is a critical step in many natural language processing and Information retrieval applications. In this paper, we introduce AKEA, a keyphrase extraction algorithm for single Arabic documents. AKEA is an unsupervised algorithm as it does not need any type of training in order to achieve its task. We rely on heuristics that collaborate linguistic patterns based on Part-Of-Speech (POS) tags, statistical knowledge, and the internal structural pattern of terms (i.e. word-occurrence). We employ the usage of Arabic Wikipedia to improve the ranking (or significance) of candidate keyphrases by adding a confidence score if the candidate exist as an indexed Wikipedia concept. Experimental results show that on average AKEA has the highest precision value, the highest F-measure value which indicates it presents more accurate results compared to its other algorithms.

KW - Keyphrase extraction

KW - Natural language processing

UR - http://www.scopus.com/inward/record.url?scp=84994531647&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-48308-5_14

DO - 10.1007/978-3-319-48308-5_14

M3 - Conference contribution

AN - SCOPUS:84994531647

SN - 9783319483078

T3 - Advances in Intelligent Systems and Computing

SP - 137

EP - 146

BT - Proceedings of the International Conference on Advanced Intelligent Systems and Informatics, 2016

A2 - Hassanien, Aboul Ella

A2 - Shaalan, Khaled

A2 - Azar, Ahmad Taher

A2 - Gaber, Tarek

A2 - Tolba, Mohamed F.

PB - Springer

Y2 - 24 October 2016 through 26 October 2016

ER -

AKEA: An Arabic keyphrase extraction algorithm

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this