@inproceedings{5d831841e3ea45f4b6152d0e3a6c1833,
title = "Farasa: A new fast and accurate Arabic word segmenter",
abstract = "In this paper, we present Farasa (meaning insight in Arabic), which is a fast and accurate Arabic segmenter. Segmentation involves breaking Arabic words into their constituent clitics. Our approach is based on SVMrank using linear kernels. The features that we utilized account for: likelihood of stems, prefixes, suffixes, and their combination; presence in lexicons containing valid stems and named entities; and underlying stem templates. Farasa outperforms or equalizes state-of-the-art Arabic segmenters, namely QATARA and MADAMIRA. Meanwhile, Farasa is nearly one order of magnitude faster than QATARA and two orders of magnitude faster than MADAMIRA. The segmenter should be able to process one billion words in less than 5 hours. Farasa is written entirely in native Java, with no external dependencies, and is open-source.",
keywords = "Arabic morphology, Stemming, Word segmentation",
author = "Kareem Darwish and Hamdy Mubarak",
year = "2016",
language = "English",
series = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
publisher = "European Language Resources Association (ELRA)",
pages = "1070--1074",
editor = "Nicoletta Calzolari and Khalid Choukri and Helene Mazo and Asuncion Moreno and Thierry Declerck and Sara Goggi and Marko Grobelnik and Jan Odijk and Stelios Piperidis and Bente Maegaard and Joseph Mariani",
booktitle = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
note = "10th International Conference on Language Resources and Evaluation, LREC 2016 ; Conference date: 23-05-2016 Through 28-05-2016",
}