DOCSLIB.ORG

A Consistent Persian Orthography Based on the Latin Script

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
A Consistent Persian Orthography Based on the Latin Script SLPO: A Consistent Persian Orthography Based on the Latin Script Reza Salarmehr Amirkabir University [email protected] Abstract Persian is officially written in Arabic script which causes some well-known problems in writing academic materialfor native and non-native speakers. In this paper we propose a standard romanization and orthography scheme for Persian named SLPO that is best fitted for natural language processing, learning purposes and writing academic material (but not limited to) and we claim that it is the most comprehensive and consistent scheme ever presented for this language. Keywords: romanization scheme, Persian, natural language processing, orthography 1 Introduction 2 The Arabic Script Problems In Iran and Afghanistan, Persian is officially written in Arabic The problems of the Arabic script for writing Persian have script that is a right to left script (RTL). In this script short been investigated extensively during the two last centuries [?]. vowels are usually not written, and as a result a lot of word- A complete review of this topic is out of the scope of this pa- forms have more than one pronunciation and meaning (e.g: per. Here, we point to two main enigma regarding using the This fact makes writing and reading Persian hard Arabic script to write Persian (For a comprehensive overview .(ﺳﯿﺮ، ﺑﺮ، ﮐﺮم for non-native (and even native) speakers [?]. As a result most of related literature refer to [?]) . authors prefer to use a romanized form of Persian words that is easier to read and is supported better in computer environ- 2.1 Short Vowel Enigma ments. However, the absence of an accepted romanization stan- Short vowels (/æ/, /e/, /o/) are not generally represented in dard caused authors to use various personal romanization written Persian while changing the short vowel in a word can -rep ‹ﮔﻞ› schemes that in turn caused some problems. In this paper, create a totally unrelated new word. As an example we represent two romanization schemes for two distinct use- resents two unrelated words: ‹gel› (mud) and ‹gol› (flower). cases. We claim that they are the most suitable schemes avail- So correct pronunciation of words which contains a short able to be used in general and particularly in academic cases. vowel is not possible without prior knowledge and if a word- The first scheme is intended to be used for general applica- form represents more that one word, the reader should choose tions but it is not totally reversible, and the second one is in- correct pronunciation according to its context. As a real ex- tended to be used in situations that reversibility is important. ample see ?? figure. The name of a single alley could notbe We have provided a web site that contains the Latin form of pronounced correctly by the mayoralty staffer and is roman- more than 350,000 Persian words and idioms. You can access ized differently on two signboards in the alley. it in http://vajje.com. Ezafe is a one of most important grammatical features of The structure of this paper is as follows: in the next sec- Persian. Ezafe is pronounced as a short vowel, /e/, and similar tion we draw an overview of related works. In section ?? we to other short vowels it is generally not written. If the word point to characteristics of our proposed orthography named preceding Ezafe ends in a vowel, Ezafe will be articulated /je/ Also there is no .‹ی› ,SLPO. In sections ?? and ?? romanization and orthography is- and it will have a written presentation sues are discussed respectively. consensus on how to write the Persian indefinite article when may be ‹ی›+‹ﺧﺎﻧﻪ› the referent ends in /e/. As an example 1 3 Related works In this section, we overview Persian romanization schemes that have been proposed in the past twenty years. Maleki [?] proposed a romanization scheme which con- tains 29 phonemes (23 consonants and 6 vowels) named Dabire (formerly eFarsi [?]). Dabire uses a single Latin grapheme for Arabic graphemes that have the same phonol- ogy in Persian. The author provides some guidelines for writ- Figure 1: Two signboards in Tehran. The name of the alley, ing compound words, abbreviations and foreign load words. ‹ ›, could not be pronounced correctly and is romanized -He also describes capitalization and punctuation in his ro ﭘﺸﻦ in two different forms in the same alley. manization scheme. Ghayour [?] provides a romanization mapping table named Ironic. Using the letter ‹w› to represent /u:/, his .[?] ‹ﺧﺎﻧﻪ ﺋﯽ› or ‹ﺧﺎﻧﻪ ﯾﯽ› ,‹ﺧﺎﻧﻪ ای› wrote as scheme only includes basic Latin alphabet. In his scheme let- ters ‹a›, ‹e›, ‹o›, ‹i›, ‹u› and ‹w› respectively represent /æ/, 2.2 ZWNJ Enigma /e/, /ɒ:/, /i:/, /o/ and /u:/. Unfortunately, this caused the Appearance of Arabic letters changes depending on the let- well-known pronunciation of letters ‹o›, ‹u›, ‹j› and ‹w› ters that precede or succeed them in a word and the struc- to be changed. Currently, Iranians generally pronounce these ture of the word that the letter belongs to. For exam- letters /o/, /uː/, /ʤ/ and /v/, respectively. Furthermore it uses a digraph for /ʤ/ and a monograph for /ʒ/ while /ʒ/ has ‹ﺳـ›,‹ـﺲ›,‹س› :has these forms (‹س›) ple, the letter sin .When writing Persian compound words, some the least frequency in Persian .‹ـﺴـ› and times letters in the concatenation point join each other Moslehi [?] introduced a romanization scheme named and sometimes they not (e.g. IPA2 (Pársik). He uses a lot of diacritics to represent aiyn (‹ﮔﻼب› →‹آب›+‹ﮔﻞ› .e.g) In computer ty- and hamza (called mul in IPA2). He also used a digraph for .(‹ﺟﺴﺘﻪ ﮔﺮﯾﺨﺘﻪ› →‹ﮔﺮﯾﺨﺘﻪ›+ZWNJ+‹ﺟﺴﺘﻪ› is a frequent Persian ‹ش› pography a zero width non-joiner character (ZWNJ) is in- /ʃ/ and a monograph for /ʧ/, while has very low frequency in Persian. The letter ‹چ› serted between stems to prevent them from joining each letter and mowz›. The› = ‹ﻣﻮز› .other. Unfortunately, there is no accepted rule for writing ‹w› is also used in some words, e.g derived and compound words (e.g. ‹dunecjoo› is written as scheme also has some rules for writing in informal language .and some other guidelines .[? ,? ,? ,?] (‹داﻧﺶ ﺟﻮ› and ‹داﻧﺸﺠﻮ› Similar to other Semitic languages, Arabic has a noncon- Mahdavi [?] proposed a strict mapping from Arabic script catenative "root-and-pattern" morphology. The pattern can to Latin script that maintains all Arabic diacritics and even The .‹(ڡ› .be used to read words correctly even without presenting short radical and ambiguous forms of letters (e.g vowels. Compounding and derivation are not used in the Ara- scheme contains almost 80 characters. Actually, adding Ara- bic language to form new words. As a result, the above two bic diacritics to Persian texts is simpler to learn and use. Nev- enigmas are not relevant in that language. Indeed the Arabic ertheless his suggestion may be useful in processing the old script only works well for writing the Arabic language. Persian and Arabic manuscripts. There are also some other rudimentary schemes, in- 2.3 Why is a standard romanization scheme nec- cluding: The Tajik alphabet in Latin (obsolete), Paarsi [?], essary? UniPers [?], UN romanization of Persian for Geographical Names [?], Library of Congress/American Library Associa- In addition to the above issues, there are some other diffi- tion romanization of Persian, IJMES transliteration system culties that caused those whose first language is not Persian for Arabic, Persian, and Turkish [?], Encyclopaedia Iranica’s to use the Latin script, instead of the Arabic script during scheme [?]. their learning course or in their publications. Unfortunately, All proposed schemes suffer from at least two of the fol- each author uses her/his personal romanization scheme that lowing deficiencies: (i) they use some new or modified Latin makes reading and indexing of romanized Persian texts diffi- letters that make their use hard for Persian-learners. (ii) they cult. Even in Iran when there is a need to romanize the name ignore phonological rules of Persian and spell some words un- of people and places, there is no unique accepted romaniza- necessarily long (iii) they lack a firm rule for writing saken ayin tion scheme. Consequently different romanized forms may and hamza. (iii) they do not comprehensively describe or- be used by distinct users which make searching the name of thography of all Persian grammatical structures. (iv) they do people and places hard and confusing. 2 not suggest a romanization scheme in situations in which re- 5 General Romanization versibility matters. (v) they ignore the semantic accepts of the writing system and do not provide any clues to shed light on The Latin script of Persian consists of 25 letters. It does not the meaning of words (vi) they do not provide a firm regular use the letter ‹w›. You can see the letters in table ??. There method to spell Persian verbs. are some rules in using this alphabet as follow: In this paper we have proposed a new orthography scheme which addresses all of these issues. Rule 1 Each word contains at least one vowel letter (‹a,e,i,o,u›). 4 SLPO Rule 2 No word begins with more than two consonants. In this section we introduce our suggested romanization See section ?? to see how to pronounce words that begin schema named Standard Latin-based Persian orthography ab- with two consonants. breviated as SLPO. In developing our romanization scheme we used some 5.1 Vowels statistics data such as letter frequency and phoneme fre- quency. You can see Persian letter frequency in figure ?? and Persian has six vowels, including: /ɒː/, /e/, /o/,/æ/, /iː/ and ??. /uː/. The first three rows of table ?? show how a single word- SLPO is the most comprehensive and consistent Persian form in the Arabic script can be pronounced differently and romanization scheme ever proposed.
Load more

Recommended publications
  • Arabic Alphabet - Wikipedia, the Free Encyclopedia Arabic Alphabet from Wikipedia, the Free Encyclopedia
    2/14/13 Arabic alphabet - Wikipedia, the free encyclopedia Arabic alphabet From Wikipedia, the free encyclopedia َأﺑْ َﺠ ِﺪﯾﱠﺔ َﻋ َﺮﺑِﯿﱠﺔ :The Arabic alphabet (Arabic ’abjadiyyah ‘arabiyyah) or Arabic abjad is Arabic abjad the Arabic script as it is codified for writing the Arabic language. It is written from right to left, in a cursive style, and includes 28 letters. Because letters usually[1] stand for consonants, it is classified as an abjad. Type Abjad Languages Arabic Time 400 to the present period Parent Proto-Sinaitic systems Phoenician Aramaic Syriac Nabataean Arabic abjad Child N'Ko alphabet systems ISO 15924 Arab, 160 Direction Right-to-left Unicode Arabic alias Unicode U+0600 to U+06FF range (http://www.unicode.org/charts/PDF/U0600.pdf) U+0750 to U+077F (http://www.unicode.org/charts/PDF/U0750.pdf) U+08A0 to U+08FF (http://www.unicode.org/charts/PDF/U08A0.pdf) U+FB50 to U+FDFF (http://www.unicode.org/charts/PDF/UFB50.pdf) U+FE70 to U+FEFF (http://www.unicode.org/charts/PDF/UFE70.pdf) U+1EE00 to U+1EEFF (http://www.unicode.org/charts/PDF/U1EE00.pdf) Note: This page may contain IPA phonetic symbols. Arabic alphabet ا ب ت ث ج ح خ د ذ ر ز س ش ص ض ط ظ ع en.wikipedia.org/wiki/Arabic_alphabet 1/20 2/14/13 Arabic alphabet - Wikipedia, the free encyclopedia غ ف ق ك ل م ن ه و ي History · Transliteration ء Diacritics · Hamza Numerals · Numeration V · T · E (//en.wikipedia.org/w/index.php?title=Template:Arabic_alphabet&action=edit) Contents 1 Consonants 1.1 Alphabetical order 1.2 Letter forms 1.2.1 Table of basic letters 1.2.2 Further notes
    [Show full text]
  • Diacritic-Based Matching of Arabic Words. ACM Trans
    Diacritic-Based Matching of Arabic Words MUSTAFA JARRAR, Birzeit University, Palestine FADI ZARAKET, American University, Lebanon 10 RAMI ASIA and HAMZEH AMAYREH, Birzeit University, Palestine Words in Arabic consist of letters and short vowel symbols called diacritics inscribed atop regular letters. Changing diacritics may change the syntax and semantics of a word; turning it into another. This results in difficulties when comparing words based solely on string matching. Typically, Arabic NLP applications resort to morphological analysis to battle ambiguity originating from this and other challenges. In this article, we introduce three alternative algorithms to compare two words with possibly different diacritics. We propose the Subsume knowledge-based algorithm, the Imply rule-based algorithm, and the Alike machine-learning- based algorithm. We evaluated the soundness, completeness, and accuracy of the algorithms against a large dataset of 86,886 word pairs. Our evaluation shows that the accuracy of Subsume (100%), Imply (99.32%), and Alike (99.53%). Although accurate, Subsume was able to judge only 75% of the data. Both Subsume and Imply are sound, while Alike is not. We demonstrate the utility of the algorithms using a real-life use case – in lemma disambiguation and in linking hundreds of Arabic dictionaries. CCS Concepts: • Computing methodologies → Natural language processing; Phonology/ morphology; Language resources; Additional Key Words and Phrases: Arabic, diacritics, disambiguation ACM Reference format: Mustafa Jarrar, Fadi Zaraket, Rami Asia, and Hamzeh Amayreh. 2018. Diacritic-Based Matching of Arabic Words. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 18, 2, Article 10 (December 2018), 21 pages. https://doi.org/10.1145/3242177 1 INTRODUCTION Diacritics are distinguishing features of the Arabic language.
    [Show full text]
  • Mpub10110094.Pdf
    An Introduction to Chaghatay: A Graded Textbook for Reading Central Asian Sources Eric Schluessel Copyright © 2018 by Eric Schluessel Some rights reserved This work is licensed under the Creative Commons Attribution-NonCommercial- NoDerivatives 4.0 International License. To view a copy of this license, visit http:// creativecommons.org/licenses/by-nc-nd/4.0/ or send a letter to Creative Commons, PO Box 1866, Mountain View, California, 94042, USA. Published in the United States of America by Michigan Publishing Manufactured in the United States of America DOI: 10.3998/mpub.10110094 ISBN 978-1-60785-495-1 (paper) ISBN 978-1-60785-496-8 (e-book) An imprint of Michigan Publishing, Maize Books serves the publishing needs of the University of Michigan community by making high-quality scholarship widely available in print and online. It represents a new model for authors seeking to share their work within and beyond the academy, offering streamlined selection, production, and distribution processes. Maize Books is intended as a complement to more formal modes of publication in a wide range of disciplinary areas. http://www.maizebooks.org Cover Illustration: "Islamic Calligraphy in the Nasta`liq style." (Credit: Wellcome Collection, https://wellcomecollection.org/works/chengwfg/, licensed under CC BY 4.0) Contents Acknowledgments v Introduction vi How to Read the Alphabet xi 1 Basic Word Order and Copular Sentences 1 2 Existence 6 3 Plural, Palatal Harmony, and Case Endings 12 4 People and Questions 20 5 The Present-Future Tense 27 6 Possessive
    [Show full text]
  • The Unicode Standard, Version 6.2 Copyright © 1991–2012 Unicode, Inc
    The Unicode Standard Version 6.2 – Core Specification To learn about the latest version of the Unicode Standard, see http://www.unicode.org/versions/latest/. Many of the designations used by manufacturers and sellers to distinguish their products are claimed as trademarks. Where those designations appear in this book, and the publisher was aware of a trade- mark claim, the designations have been printed with initial capital letters or in all capitals. Unicode and the Unicode Logo are registered trademarks of Unicode, Inc., in the United States and other countries. The authors and publisher have taken care in the preparation of this specification, but make no expressed or implied warranty of any kind and assume no responsibility for errors or omissions. No liability is assumed for incidental or consequential damages in connection with or arising out of the use of the information or programs contained herein. The Unicode Character Database and other files are provided as-is by Unicode, Inc. No claims are made as to fitness for any particular purpose. No warranties of any kind are expressed or implied. The recipient agrees to determine applicability of information provided. Copyright © 1991–2012 Unicode, Inc. All rights reserved. This publication is protected by copyright, and permission must be obtained from the publisher prior to any prohibited reproduction. For information regarding permissions, inquire at http://www.unicode.org/reporting.html. For information about the Unicode terms of use, please see http://www.unicode.org/copyright.html. The Unicode Standard / the Unicode Consortium ; edited by Julie D. Allen ... [et al.]. — Version 6.2.
    [Show full text]
  • Through the Looking-Glass: Roman Letters in Phonics for Arabic As a Part of Multimedia Support
    Recent Technological Advances in Education Through the Looking-Glass: Roman letters in phonics for Arabic as a part of multimedia support MOSA AHMED EBRAHIM MOHAMED Computer Science Department WASEDA University Okubo, Shinjuku-ku, Tokyo JAPAN Educational Technology Department TANTA University Tanta, Al Gharbya EGYPT [email protected] KAKEHI KATSUHIKO Computer Science Department WASEDA University Okubo, Shinjuku-ku, Tokyo JAPAN [email protected] Abstract: - As a part of multi-media support system for Arabic e-learning, some vehicle should be provided for training students to pronounce Arabic text themselves. Since the Arabic alphabet is phonetic, it seems a good idea to transliterate Arabic into Roman, the most popular language, but there exists a big gap between Arabic and Roman besides a difference between their alphabets; scripting directions. Arabic script is written from right to left, whereas Roman from left to right. What kind of transliteration would let students jump over this gap? Our solution is to render transliteration results as if seen Through the Looking-Glass. We report our process of trials and errors for seeking solutions, and our ultimate solution. Key-Words: - E-Learning, Multimedia supporting, Arabic learning, Arabic transliteration. 1 Introduction We are living in the age of the e-Learning and Islamic religion and Arabian countries are multimedia. This is why there is an increasing need increasing their presence in the world. The Arabic for cultural exchange and language learning all over language is one of the most popular languages in the the world. Also there is wide range of demand for world, as there are about fifty seven Islamic learning Arabic worldwide.
    [Show full text]
  • Exploiting Arabic Diacritization for High Quality Automatic Annotation
    Exploiting Arabic Diacritization for High Quality Automatic Annotation Nizar Habash, Anas Shahrour, Muhamed Al-Khalil Computational Approaches to Modeling Language Lab New York University Abu Dhabi, UAE {nizar.habash,anas.shahrour,muhamed.alkhalil}@nyu.edu Abstract We present a novel technique for Arabic morphological annotation. The technique utilizes diacritization to produce morphological annotations of quality comparable to human annotators. Although Arabic text is generally written without diacritics, diacritization is already available for large corpora of Arabic text in several genres. Furthermore, diacritization can be generated at a low cost for new text as it does not require specialized training beyond what educated Arabic typists know. The basic approach is to enrich the input to a state-of-the-art Arabic morphological analyzer with word diacritics (full or partial) to enhance its performance. When applied to fully diacritized text, our approach produces annotations with an accuracy of over 97% on lemma, part-of-speech, and tokenization combined. Keywords: Arabic, Morphology, Annotation, Diacritization 1. Introduction Arabic resources (the taggers and analyzers) that facilitate The automatic processing of the Arabic language is chal- it. The idea is also applicable to other languages with sim- lenging for a number of reasons. Two inter-related reasons ilar orthographic ambiguity challenges, e.g., Hebrew and are Arabic’s complex morphology and its diacritic-optional Persian. Our results on Arabic show that using our ap- orthography (Habash, 2010). This combination leads to proach produces quality comparable to human manual an- the high number of about 12.8 possible analyses per word notation (Maamouri et al., 2008; Habash and Roth, 2009) out of context (Shahrour et al., 2015).
    [Show full text]
  • Diacritics Restoration for Arabic Dialects Salima Harrat, Mourad Abbas, Karima Meftouh, Kamel Smaïli
    Diacritics Restoration for Arabic Dialects Salima Harrat, Mourad Abbas, Karima Meftouh, Kamel Smaïli To cite this version: Salima Harrat, Mourad Abbas, Karima Meftouh, Kamel Smaïli. Diacritics Restoration for Arabic Dialects. INTERSPEECH 2013 - 14th Annual Conference of the International Speech Communication Association, ISCA, Aug 2013, Lyon, France. hal-00925815 HAL Id: hal-00925815 https://hal.inria.fr/hal-00925815 Submitted on 8 Jan 2014 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. Diacritics restoration for Arabic dialect texts S. Harrat1, M. Abbas2, K. Meftouh3, K. Smaili4 1ENS Bouzareah, Algiers, Algeria 2CRSTDLA, Algiers, Algeria 3Badji Mokhtar University-Annaba, Algeria 4Campus scientifique LORIA , Nancy, France [email protected], m [email protected], [email protected], [email protected] Abstract nally, we worked first on MSA texts because of the available results for many works in this field. In this paper we present a statistical approach for automatic di- This paper is organised as follows: In section 2, we describe acritization of Algiers dialectal texts. This approach is based the Arabic language and present the main features of this lan- on statistical machine translation. We first investigate this ap- guage especially those related to diacritization.
    [Show full text]
  • Middle East-I 9 Modern and Liturgical Scripts
    The Unicode® Standard Version 13.0 – Core Specification To learn about the latest version of the Unicode Standard, see http://www.unicode.org/versions/latest/. Many of the designations used by manufacturers and sellers to distinguish their products are claimed as trademarks. Where those designations appear in this book, and the publisher was aware of a trade- mark claim, the designations have been printed with initial capital letters or in all capitals. Unicode and the Unicode Logo are registered trademarks of Unicode, Inc., in the United States and other countries. The authors and publisher have taken care in the preparation of this specification, but make no expressed or implied warranty of any kind and assume no responsibility for errors or omissions. No liability is assumed for incidental or consequential damages in connection with or arising out of the use of the information or programs contained herein. The Unicode Character Database and other files are provided as-is by Unicode, Inc. No claims are made as to fitness for any particular purpose. No warranties of any kind are expressed or implied. The recipient agrees to determine applicability of information provided. © 2020 Unicode, Inc. All rights reserved. This publication is protected by copyright, and permission must be obtained from the publisher prior to any prohibited reproduction. For information regarding permissions, inquire at http://www.unicode.org/reporting.html. For information about the Unicode terms of use, please see http://www.unicode.org/copyright.html. The Unicode Standard / the Unicode Consortium; edited by the Unicode Consortium. — Version 13.0. Includes index. ISBN 978-1-936213-26-9 (http://www.unicode.org/versions/Unicode13.0.0/) 1.
    [Show full text]
  • Arabic Alphabet 1 Arabic Alphabet
    Arabic alphabet 1 Arabic alphabet Arabic abjad Type Abjad Languages Arabic Time period 400 to the present Parent systems Proto-Sinaitic • Phoenician • Aramaic • Syriac • Nabataean • Arabic abjad Child systems N'Ko alphabet ISO 15924 Arab, 160 Direction Right-to-left Unicode alias Arabic Unicode range [1] U+0600 to U+06FF [2] U+0750 to U+077F [3] U+08A0 to U+08FF [4] U+FB50 to U+FDFF [5] U+FE70 to U+FEFF [6] U+1EE00 to U+1EEFF the Arabic alphabet of the Arabic script ﻍ ﻉ ﻅ ﻁ ﺽ ﺹ ﺵ ﺱ ﺯ ﺭ ﺫ ﺩ ﺥ ﺡ ﺝ ﺙ ﺕ ﺏ ﺍ ﻱ ﻭ ﻩ ﻥ ﻡ ﻝ ﻙ ﻕ ﻑ • history • diacritics • hamza • numerals • numeration abjadiyyah ‘arabiyyah) or Arabic abjad is the Arabic script as it is’ ﺃَﺑْﺠَﺪِﻳَّﺔ ﻋَﺮَﺑِﻴَّﺔ :The Arabic alphabet (Arabic codified for writing the Arabic language. It is written from right to left, in a cursive style, and includes 28 letters. Because letters usually[7] stand for consonants, it is classified as an abjad. Arabic alphabet 2 Consonants The basic Arabic alphabet contains 28 letters. Adaptations of the Arabic script for other languages added and removed some letters, such as Persian, Ottoman, Sindhi, Urdu, Malay, Pashto, and Arabi Malayalam have additional letters, shown below. There are no distinct upper and lower case letter forms. Many letters look similar but are distinguished from one another by dots (’i‘jām) above or below their central part, called rasm. These dots are an integral part of a letter, since they distinguish between letters that represent different sounds.
    [Show full text]
  • Diacritization of a Highly Cited Text: a Classical Arabic Book As a Case
    This is a repository copy of Diacritization of a Highly Cited Text: A Classical Arabic Book as a Case. White Rose Research Online URL for this paper: http://eprints.whiterose.ac.uk/128591/ Version: Accepted Version Proceedings Paper: Alosaimy, A and Atwell, E orcid.org/0000-0001-9395-3764 (2018) Diacritization of a Highly Cited Text: A Classical Arabic Book as a Case. In: Proceedings of ASAR'2018 Arabic Script Analysis and Recognition. ASAR'2018 Arabic Script Analysis and Recognition, 12-14 Mar 2018, Alan Turing Institute, The British Library, London UK. IEEE , pp. 72-77. © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Reuse Unless indicated otherwise, fulltext items are protected by copyright with all rights reserved. The copyright exception in section 29 of the Copyright, Designs and Patents Act 1988 allows the making of a single copy solely for the purpose of non-commercial research or private study within the limits of fair dealing. The publisher or other rights-holder may allow further reproduction and re-use of this version - refer to the White Rose Research Online record for this item. Where records identify the publisher as the copyright holder, users can verify any specific terms of use on the publisher’s website. Takedown If you consider content in White Rose Research Online to be in breach of UK law, please notify us by emailing [email protected] including the URL of the record and the reason for the withdrawal request.
    [Show full text]
  • Arabic Diacritics 1 Arabic Diacritics
    Arabic diacritics 1 Arabic diacritics Arabic alphabet ﻱ ﻭ ﻩ ﻥ ﻡ ﻝ ﻙ ﻕ ﻑ ﻍ ﻉ ﻅ ﻁ ﺽ ﺹ ﺵ ﺱ ﺯ ﺭ ﺫ ﺩ ﺥ ﺡ ﺝ ﺙ ﺕ ﺏ ﺍ Arabic script • History • Transliteration • Diacritics • Hamza • Numerals • Numeration • v • t [1] • e 〈ﺗَﺸْﻜِﻴﻞ〉 i‘jām, consonant pointing), and tashkil) 〈ﺇِﻋْﺠَﺎﻡ〉 The Arabic script has numerous diacritics, including i'jam .(〈ﺣَﺮَﻛَﺔ〉 vowel marks; singular: ḥarakah) 〈ﺣَﺮَﻛَﺎﺕ〉 tashkīl, supplementary diacritics). The latter include the ḥarakāt) The Arabic script is an impure abjad, where short consonants and long vowels are represented by letters but short vowels and consonant length are not generally indicated in writing. Tashkīl is optional to represent missing vowels and consonant length. Modern Arabic is nearly always written with consonant pointing, but occasionally unpointed texts are still seen. Early texts such as the Qur'an were initially written without pointing, and pointing was added later to determine the expected readings and interpretations. Tashkil (marks used as phonetic guides) The literal meaning of tashkīl is 'forming'. As the normal Arabic text does not provide enough information about the correct pronunciation, the main purpose of tashkīl (and ḥarakāt) is to provide a phonetic guide or a phonetic aid; i.e. show the correct pronunciation. It serves the same purpose as furigana (also called "ruby") in Japanese or pinyin or zhuyin in Mandarin Chinese for children who are learning to read or foreign learners. The bulk of Arabic script is written without ḥarakāt (or short vowels). However, they are commonly used in some al-Qur’ān). It is not) 〈ﺍﻟْﻘُﺮْﺁﻥ〉 religious texts that demand strict adherence to pronunciation rules such as Qur'an al-ḥadīth; plural: aḥādīth) as well.
    [Show full text]
  • Guidelines and Framework for a Large Scale Arabic Diacritized Corpus
    Guidelines and Framework for a Large Scale Arabic Diacritized Corpus Wajdi Zaghouani1, Houda Bouamor1, Abdelati Hawwari2, Mona Diab 2, Ossama Obeid1, Mahmoud Ghoneim2, Sawsan Alqahtani2 and Kemal Oflazer1 1Carnegie Mellon University in Qatar fwajdiz,hbouamor,[email protected], [email protected] 2George Washington University fmdiab,abhawwari,ghoneim,[email protected] Abstract This paper presents the annotation guidelines developed as part of an effort to create a large scale manually diacritized corpus for various Arabic text genres. The target size of the annotated corpus is 2 million words. We summarize the guidelines and describe issues encountered during the training of the annotators. We also discuss the challenges posed by the complexity of the Arabic language and how they are addressed. Finally, we present the diacritization annotation procedure and detail the quality of the resulting annotations. Keywords: Arabic Diacritization, Guidelines, Annotation 1. Introduction Undiacritized Diacritized Buckwalter English Written Modern Standard Arabic (MSA) poses many chal- Y«ð Y«ð /waEad/ he promised lenges for natural language processing (NLP). Most written Y«ð Y« ð /waEodN/ it/a promise Arabic text lacks short vowels and diacritics rendering a Y«ð Y« ð /wuEida/ he was promised mostly consonantal orthography (Schulz, 2004). Arabic di- Y«ð Y« ð /waEad ˜a/ and he counted acritization is an orthographic way to describe Arabic word /waEud ˜a/ and he was counted pronunciation, and to avoid word reading ambiguity. Ara- Y«ð Y«ð bic writing system has two classes of symbols: letters and diacritics. diacritics are the marks that reflect the phonolog- Table 1: Possible pronunciations and meanings of the undi- ical, morphological and grammatical rules.
    [Show full text]