Buckwalter Arabic Morphological Analyzer Version 1.0

Item Name: Buckwalter Arabic Morphological Analyzer Version 1.0
Authors: Tim Buckwalter
LDC Catalog No.: LDC2002L49
ISBN: 1-58563-257-0
Release Date: Nov 08, 2002
Data Type: lexicon
Data Source(s): dictionaries
Project(s): GALE, TIDES
Application(s): information retrieval, machine translation, natural language processing
Language(s): Modern Standard Arabic
Language ID(s): ARB
Distribution: Web Download
Member fee: $0 for members
Non-member Fee: US $150.00
Reduced-License Fee: US $150.00
Extra-Copy Fee: US $150.00
Online documentation: yes
Licensing Instructions: Subscription & Standard Members, and Non-Members
Citation: Tim Buckwalter
Buckwalter Arabic Morphological Analyzer Version 1.0
Linguistic Data Consortium, Philadelphia


Buckwalter Arabic Morphological Analyzer Version 1.0 was produced by Linguistic Data Consortium (LDC), catalog number LDC2002L49 and ISBN 1-58563-257-0. The Buckwalter Arabic Morphological Analyzer is used for POS-tagging Arabic text.


The data consists primarily of three Arabic-English lexicon files: prefixes (299 entries), suffixes (618 entries), and stems (82,158 entries representing 38,600 lemmas). The lexicons are supplemented by three morphological compatibility tables used for controlling prefix-stem combinations (1,648 entries), stem-suffix combinations (1,285 entries), and prefix-suffix combinations (598 entries). The actual code for morphology analysis and POS tagging is contained in a Perl script. The documentation consists of a readme file with a description of the lexicon files, the morphological compatibility tables, the morphology analysis algorithm, a summary of stem morphological categories, and a table with the author's Arabic transliteration system.


There has been a case mismatch in the manner by which six files were named in the data, compared with their names in the documentation and the script, which caused the analyzer to crash on case sensitive systems. This problem has been remedied and you can now download the fixed version of the analyzer.

Content Copyright

Portions 2002 QAMUS LLC (www.qamus.org), 2002 Trustees of the University of Pennsylvania

The Linguistic Data Consortium is releasing this software under the GNU General Public License; organizations interested in licensing the lexicon and/or morphological analyzer for commercial use should contact: QAMUS LLC 448 South 48th St. Philadelphia, PA 19143 ATTN: Tim Buckwalter email: info@qamus.org


This corpus is free of charge as a web download distribution; a request must be submitted to ldc@ldc.upenn.edu to obtain the data. Note that there is a $100 charge if requested on a CD-ROM.