@inproceedings{08efbb26ac70479a8cb04561fdf15e59,
title = "Can crowdsourcing be used for effective annotation of Arabic?",
abstract = "Crowdsourcing has been used recently as an alternative to traditional costly annotation by many natural language processing groups. In this paper, we explore the use of Amazon Mechanical Turk (AMT) in order to assess the feasibility of using AMT workers (also known as Turkers) to perform linguistic annotation of Arabic. We used a gold standard data set taken from the Quran corpus project annotated with part-of-speech and morphological information. An Arabic language qualification test was used to filter out potential non-qualified participants. Two experiments were performed, a part-of-speech tagging task in where the annotators were asked to choose a correct word-category from a multiple choice list and case ending identification task. The results obtained so far showed that annotating Arabic grammatical case is harder than POS tagging, and crowdsourcing for Arabic linguistic annotation requiring expert annotators could be not as effective as other crowdsourcing experiments requiring less expertise and qualifications.",
keywords = "Annotation, Arabic, Crowdsourcing",
author = "Wajdi Zaghouani and Kais Dukes",
year = "2014",
language = "English",
series = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
publisher = "European Language Resources Association (ELRA)",
pages = "224--228",
editor = "Nicoletta Calzolari and Khalid Choukri and Sara Goggi and Thierry Declerck and Joseph Mariani and Bente Maegaard and Asuncion Moreno and Jan Odijk and Helene Mazo and Stelios Piperidis and Hrafn Loftsson",
booktitle = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
note = "9th International Conference on Language Resources and Evaluation, LREC 2014 ; Conference date: 26-05-2014 Through 31-05-2014",
}