Introduction

Welcome to the homepage of Urdu Morphology. We provide an Urdu Morphological Analyzer & Generator which is developed by using Functional Morphology (FM) as a Master thesis under the supervision of Prof. Aarne Ranta at Language Technology group, Department of Computer science, Chalmers University of technology, Sweden. Harald Hammarström was also involved in this project quite extensively to review the work.

We provide following components as a software package which is available to download below under GNU General Public License:

• An implementation of Urdu morphology as an open source software.
• A lexicon of 4163 words and 96840 word forms.
• A manual for users/lexicographers to add new words into the lexicon
• An implementation of a small part of Urdu syntax in Grammatical Framework by reusing the above mentioned resources
• A Unicode Infrastructure for the Urdu morphology API to accommodate Perso-Arabic script of Urdu including a GUI application and useful tools

NEW

• A user experience on using Urdu morphological analyzer is posted by Mr. Shakir Aziz on his Urdu blog. He is an MS student in Linguistics and also blog in English which could be read here. I am grateful for his well written review.

Documentation

• User & Install Manual
• Manual for Lexicographers

Publications related to this work

• Implementing Urdu Grammar as Open Source Software - extended abstract. For the tutorial given at Conference on Language and Technology, August 07-11, 2007, University of Peshawar, Pakistan. (pdf) (presentation)

• M. Humayoun, H. Hammarström, and A. Ranta. Urdu Morphology, Orthography and Lexicon Extraction. CAASL-2: The Second Workshop on Computational Approaches to Arabic Script-based Languages, July 21-22, 2007, LSA 2007 Linguistic Institute, Stanford University. 2007. (Design decision of version 1.2 are based on this paper) (pdf) (presentation)

• M. Humayoun. Urdu Morphology, Orthography and Lexicon Extraction. Master’s Thesis, Department of Computing Science, Chalmers University of Technology, 2006. (pdf) (slightly old with respect to version 1.2) as the file is big (2.78Mb) please "right click -> Save Target As" to download

Downloads (Source code)

• Urdu Morphology Application Source code
• Urdu lexicon (Ascii)
• Urdu lexicon (Unicode, UTF-8)
• screenshot1, screenshot2, screenshot3, screenshot4

Links

• Functional Morphology
• Grammatical Framework
• Urdu Book bank, blogs, wiki etc

Please send your feedback and suggestions at humayoun{@}gmail.com

---

Last update: Mon Oct 25 22:04:44 2010