Home > Research > Publications & Outputs > AraSAS

Research

Associated organisational units

Links

View graph of relations

AraSAS: The Open Source Arabic Semantic Tagger

Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review

Published

Standard

AraSAS: The Open Source Arabic Semantic Tagger. / El-Haj, Mahmoud; Rayson, Paul; de Souza, Elvis et al.
2022. 23-31 Paper presented at Open-Source Arabic Corpora and Processing Tools, Marseille, France.

Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review

Harvard

El-Haj, M, Rayson, P, de Souza, E, Khallaf, N & Habash, N 2022, 'AraSAS: The Open Source Arabic Semantic Tagger', Paper presented at Open-Source Arabic Corpora and Processing Tools, Marseille, France, 20/06/22 - 20/06/22 pp. 23-31. <http://www.lrec-conf.org/proceedings/lrec2022/workshops/OSACT/bib/2022.osact-1.3.bib>

APA

El-Haj, M., Rayson, P., de Souza, E., Khallaf, N., & Habash, N. (2022). AraSAS: The Open Source Arabic Semantic Tagger. 23-31. Paper presented at Open-Source Arabic Corpora and Processing Tools, Marseille, France. http://www.lrec-conf.org/proceedings/lrec2022/workshops/OSACT/bib/2022.osact-1.3.bib

Vancouver

El-Haj M, Rayson P, de Souza E, Khallaf N, Habash N. AraSAS: The Open Source Arabic Semantic Tagger. 2022. Paper presented at Open-Source Arabic Corpora and Processing Tools, Marseille, France.

Author

El-Haj, Mahmoud ; Rayson, Paul ; de Souza, Elvis et al. / AraSAS : The Open Source Arabic Semantic Tagger. Paper presented at Open-Source Arabic Corpora and Processing Tools, Marseille, France.8 p.

Bibtex

@conference{f7f261f6cff14bd9b169b73f86920dd5,
title = "AraSAS: The Open Source Arabic Semantic Tagger",
abstract = "This paper presents (AraSAS) the first open-source Arabic semantic analysis tagging system. AraSAS is a software framework that provides full semantic tagging of text written in Arabic. AraSAS is based on the UCREL Semantic Analysis System (USAS) which was first developed to semantically tag English text. Similarly to USAS, AraSAS uses a hierarchical semantic tag set that contains 21 major discourse fields and 232 fine-grained semantic field tags. The paper describes the creation, validation and evaluation of AraSAS. In addition, we demonstrate a first case study to illustrate the affordances of applying USAS and AraSAS semantic taggers on the Zayed University Arabic-English Bilingual Undergraduate Corpus (ZAEBUC) (Palfreyman and Habash, 2022), where we show and compare the coverage of the two semantic taggers through running them on Arabic and English essays on different topics. The analysis expands to compare the taggers when run on texts in Arabic and English written by the same writer and texts written by male and by female students. Variables for comparison include frequency of use of particular semantic sub-domains, as well as the diversity of semantic elements within a text.",
author = "Mahmoud El-Haj and Paul Rayson and {de Souza}, Elvis and Nouran Khallaf and Nizar Habash",
year = "2022",
month = jun,
day = "15",
language = "English",
pages = "23--31",
note = "Open-Source Arabic Corpora and Processing Tools, OSACT 2022 ; Conference date: 20-06-2022 Through 20-06-2022",
url = "https://osact-lrec.github.io/",

}

RIS

TY - CONF

T1 - AraSAS

T2 - Open-Source Arabic Corpora and Processing Tools

AU - El-Haj, Mahmoud

AU - Rayson, Paul

AU - de Souza, Elvis

AU - Khallaf, Nouran

AU - Habash, Nizar

N1 - Conference code: 5

PY - 2022/6/15

Y1 - 2022/6/15

N2 - This paper presents (AraSAS) the first open-source Arabic semantic analysis tagging system. AraSAS is a software framework that provides full semantic tagging of text written in Arabic. AraSAS is based on the UCREL Semantic Analysis System (USAS) which was first developed to semantically tag English text. Similarly to USAS, AraSAS uses a hierarchical semantic tag set that contains 21 major discourse fields and 232 fine-grained semantic field tags. The paper describes the creation, validation and evaluation of AraSAS. In addition, we demonstrate a first case study to illustrate the affordances of applying USAS and AraSAS semantic taggers on the Zayed University Arabic-English Bilingual Undergraduate Corpus (ZAEBUC) (Palfreyman and Habash, 2022), where we show and compare the coverage of the two semantic taggers through running them on Arabic and English essays on different topics. The analysis expands to compare the taggers when run on texts in Arabic and English written by the same writer and texts written by male and by female students. Variables for comparison include frequency of use of particular semantic sub-domains, as well as the diversity of semantic elements within a text.

AB - This paper presents (AraSAS) the first open-source Arabic semantic analysis tagging system. AraSAS is a software framework that provides full semantic tagging of text written in Arabic. AraSAS is based on the UCREL Semantic Analysis System (USAS) which was first developed to semantically tag English text. Similarly to USAS, AraSAS uses a hierarchical semantic tag set that contains 21 major discourse fields and 232 fine-grained semantic field tags. The paper describes the creation, validation and evaluation of AraSAS. In addition, we demonstrate a first case study to illustrate the affordances of applying USAS and AraSAS semantic taggers on the Zayed University Arabic-English Bilingual Undergraduate Corpus (ZAEBUC) (Palfreyman and Habash, 2022), where we show and compare the coverage of the two semantic taggers through running them on Arabic and English essays on different topics. The analysis expands to compare the taggers when run on texts in Arabic and English written by the same writer and texts written by male and by female students. Variables for comparison include frequency of use of particular semantic sub-domains, as well as the diversity of semantic elements within a text.

M3 - Conference paper

SP - 23

EP - 31

Y2 - 20 June 2022 through 20 June 2022

ER -