@inproceedings{darwish-mubarak-2016-farasa,
title = "{F}arasa: A New Fast and Accurate {A}rabic Word Segmenter",
author = "Darwish, Kareem and
Mubarak, Hamdy",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1170",
pages = "1070--1074",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="darwish-mubarak-2016-farasa">
<titleInfo>
<title>Farasa: A New Fast and Accurate Arabic Word Segmenter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">darwish-mubarak-2016-farasa</identifier>
<location>
<url>https://aclanthology.org/L16-1170</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1070</start>
<end>1074</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Farasa: A New Fast and Accurate Arabic Word Segmenter
%A Darwish, Kareem
%A Mubarak, Hamdy
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F darwish-mubarak-2016-farasa
%X 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.
%U https://aclanthology.org/L16-1170
%P 1070-1074
Markdown (Informal)
[Farasa: A New Fast and Accurate Arabic Word Segmenter](https://aclanthology.org/L16-1170) (Darwish & Mubarak, LREC 2016)
ACL
- Kareem Darwish and Hamdy Mubarak. 2016. Farasa: A New Fast and Accurate Arabic Word Segmenter. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1070–1074, Portorož, Slovenia. European Language Resources Association (ELRA).