ISSN: 2534-5192 (electronic) – 2681-8566 (print)| ◀ Elti di Rodeano | ▲ Proceedings | Dürscheid & Meletis ▶ |
 ISBN: 978-2-9570549-0-9 e-ISBN: 978-2-9570549-1-6  Download (57.57 MB) | Unicode from a Linguistic Point of View Yannis Haralambous  & Martin Dürst Download (3.67 MB)Abstract. In this paper we describe and comment, from a linguistic point of view, Unicode notions pertaining to writing. After comparing characters with graphemes, glyphs with graphs and basic shapes, character general categories with grapheme classes, and character strings with graphemic sequences, we discuss two issues: the phenomenon of ligatures that stand at the boundary between graphemics and graphetics, and the proposal for the introduction of “QID emojis” which may end up being a turning point in human communication. DOI: https://doi.org/10.36824/2018-graf-hara1
@ARTICLE{schopp,
AUTHOR = {Schopp, Jürgen F.},
TITLE = {{In Gutenbergs Fußstapfen: Translatio typographica. Zum Verhältnis von
Typografie und Translation}},
JOURNAL = {Meta},
YEAR = {2008},
VOLUME = {53},
PAGES = {167--183},
}
@BOOK{myers,
AUTHOR = {Myers, James},
TITLE = {{The Grammar of Chinese Characters. Productive Knowledge of Formal Patterns
in an Orthographic System}},
PUBLISHER = {Routledge},
ADDRESS = {London, New York},
YEAR = {2019},
}
@BOOK{daniels,
AUTHOR = {Daniels, Peter and Bright, William},
TITLE = {{The World's Writing Systems}},
EDITION = {2},
PUBLISHER = {Oxford University Press},
ADDRESS = {Oxford},
YEAR = {1996},
}
@BOOK{mackenzie,
AUTHOR = {Mackenzie, Charles E.},
TITLE = {{Coded Character Sets, History and Development}},
PUBLISHER = {Addison-Wesley},
ADDRESS = {Reading, MA},
YEAR = {1980},
}
@INPROCEEDINGS{yh98ep2,
AUTHOR = {Haralambous, Yannis},
TITLE = {{Simplification of the Arabic Script: Two Different Approaches and
Their Implementations}},
BOOKTITLE = {{Electronic Publishing, Artistic Imaging, and Digital Typography}},
MAINTITLE = {{Springer Lecture Notes in Computer Science}},
YEAR = {1998},
VOLUME = {1375},
PAGES = {138--156},
}
@BOOK{mashq,
AUTHOR = {Mousavi Jazayeri, S.M.V. and Michelli, Perette E. and Abulhab, Sadd D.},
TITLE = {{A Handbook of Early Arabic Kufic Script}},
PUBLISHER = {Blautopf Publishing},
ADDRESS = {New York},
YEAR = {2017},
}
@BOOK{kazuo,
AUTHOR = {Kazuo, Inamori},
AUTHOR_ORIGINAL = {稲盛和夫},
AUTHOR+AN = {1=ja-Japn},
TITLE = {{{\japanese 心} [The Mind]}},
PUBLISHER = {{\japanese サンマーク出版} [Sunmark Publishing]},
ADDRESS = {Tokyo},
YEAR = {2019},
}
@ARTICLE{kaplan,
AUTHOR = {Kaplan, Ronald M. and Kay, Martin},
TITLE = {{Regular Models of Phonological Rule Systems}},
JOURNAL = {Computational Linguistics},
YEAR = {1994},
VOLUME = {29},
PAGES = {331--378},
}
@UNPUBLISHED{svg,
AUTHOR = {Bellamy-Royds, Amelia and others},
TITLE = {{Scalable Vector Graphics (SVG) 2}},
YEAR = {2018},
ADDENDUM = {\url{https://www.w3.org/TR/SVG2/}.},
}
@UNPUBLISHED{mathml,
AUTHOR = {Carlisle, David and Ion, Patrick and Miner, Robert},
TITLE = {{Mathematical Markup Language (MathML) Version 3.0}},
EDITION = {2},
YEAR = {2014},
ADDENDUM = {\url{https://www.w3.org/TR/MathML3/}.},
}
@BOOK{duerscheid,
AUTHOR = {Dürscheid, Christa},
TITLE = {{Einführung in die Schriftlinguistik}},
EDITION = {5},
PUBLISHER = {Vandenhoeck \& Ruprecht},
ADDRESS = {Göttingen},
YEAR = {2016},
}
@UNPUBLISHED{ruby,
AUTHOR = {Sawicki, Marcin and Suignard, Michel and Ishikawa, Masayasu and Dürst,
Martin and Texin, Tex},
TITLE = {{Ruby Annotation}},
YEAR = {2001},
ADDENDUM = {\url{https://www.w3.org/TR/2001/REC-ruby-20010531/}.},
}
@ARTICLE{folia,
AUTHOR = {van Gompel, Maarten and Reynaert, Martin},
TITLE = {{FoLiA: A Practical XML Format for Linguistic Annotation---a Descriptive
and Comparative Study}},
JOURNAL = {Computational Linguistics in the Netherlands Journal},
YEAR = {2013},
VOLUME = {3},
PAGES = {63--81},
}
@UNPUBLISHED{dcs,
AUTHOR = {Hellwig, Oliver},
TITLE = {{DCS---The Digital Corpus of Sanskrit}},
YEAR = {2010--2019},
ADDENDUM = {\url{http://www.sanskrit-linguistics.org/dcs/}},
}
@ARTICLE{dukes,
AUTHOR = {Dukes, Kais and Atwell, Eric and Habash, Nizar},
TITLE = {{Supervised Collaboration for Syntactic Annotation of Quranic Arabic}},
JOURNAL = {Language Resources and Evaluation},
YEAR = {2013},
VOLUME = {47},
NUMBER = {1},
PAGES = {33--62},
}
@UNPUBLISHED{owl,
AUTHOR = {Bao, Jie and others},
TITLE = {{OWL 2 Web Ontology Language Document Overview}},
EDITION = {2},
YEAR = {2012},
ADDENDUM = {\url{https://www.w3.org/TR/owl2-overview/}},
}
@UNPUBLISHED{rdf,
AUTHOR = {Hayes, Patrick J. and Patel-Schneider, Peter F.},
TITLE = {{RDF 1.1 Semantics}},
YEAR = {2014},
ADDENDUM = {\url{https://www.w3.org/TR/rdf11-mt/}},
}
@UNPUBLISHED{xml,
AUTHOR = {Bray, Tim and others},
TITLE = {{Extensible Markup Language (XML) 1.0}},
EDITION = {5},
YEAR = {2008},
ADDENDUM = {\url{https://www.w3.org/TR/xml/}},
}
@INPROCEEDINGS{marneffe-etal-2013-constructions,
AUTHOR = {Marneffe, Marie-Catherine de and Connor, Miriam and Silveira, Natalia
and Bowman, Samuel R. and Dozat, Timothy and Manning, Christopher D.},
TITLE = {{More Constructions, More Genres: Extending Stanford Dependencies}},
BOOKTITLE = {{Proceedings of the Second International Conference on Dependency
Linguistics (DepLing 2013)}},
PUBLISHER = {Matfyz\-press},
ADDRESS = {Prague},
YEAR = {2013},
PAGES = {187--196},
}
@UNPUBLISHED{xhtml,
AUTHOR = {Pemperton, Steven and others},
TITLE = {{XHTML 1.0 The Extensible HyperText Markup Language}},
YEAR = {2018},
ADDENDUM = {\url{https://www.w3.org/TR/xhtml1}},
}
@UNPUBLISHED{xslfo,
AUTHOR = {Berglund, Anders},
TITLE = {{Extensible Stylesheet Language (XSL) Version 1.1}},
YEAR = {2006},
ADDENDUM = {\url{https://www.w3.org/TR/xsl11/}},
}
@UNPUBLISHED{iri,
AUTHOR = {Dürst, Martin and Suignard, M.},
TITLE = {{Internationalized Resource Identifiers (IRIs)}},
YEAR = {2005},
ADDENDUM = {Request for Comments 3987},
}
@BOOK{meletis,
AUTHOR = {Meletis, Dimitrios},
TITLE = {{Graphetik. Form und Materialität von Schrift}},
PUBLISHER = {Verlag Werner Hülsbusch},
ADDRESS = {Glückstadt},
YEAR = {2015},
}
@ARTICLE{stoeckl,
AUTHOR = {Stöckl, Harmut},
TITLE = {{Typographie: Gewand und Körper des Textes -- Linguistische Überlegungen
zu typographischer Gestaltung}},
JOURNAL = {Zeitschrift für angewandte Linguistik},
YEAR = {2004},
VOLUME = {41},
PAGES = {5--48},
}
@UNPUBLISHED{meletis18,
AUTHOR = {Meletis, Dimitrios},
TITLE = {{(Re)Introducing Graphetics. The study of the materiality of writing,
its questions, and its problems}},
YEAR = {2018},
ADDENDUM = {Université Libre de Bruxelles, September 13th-14th, 2018},
}
@PHDTHESIS{meletisphd,
AUTHOR = {Meletis, Dimitrios},
TITLE = {{Naturalness in scripts and writing systems: Outlining a Natural
Grapholinguistics}},
SCHOOL = {University of Graz},
YEAR = {2019},
}
@INPROCEEDINGS{bib258,
AUTHOR = {Dürscheid, Christa},
EDITOR = {Mensching, Guido and Lalande, Jean-Yves and Hermes, Jürgen and Neuefeind, Claes},
TITLE = {{Bild, Schrift, Unicode}},
BOOKTITLE = {{Sprache -- Mensch -- Ma\-schi\-ne. Beiträge zu Sprache und
Sprachwissenschaft, Computerlinguistik und Informations\-technologie für Jürgen
Rolshoven aus Anlass seines sechsundsechzigsten Geburtstages}},
PUBLISHER = {Kölner UniversitätsPublikationsServer},
ADDRESS = {Köln},
YEAR = {2018},
PAGES = {269--285},
}
@BOOK{breton,
AUTHOR = {Wmffre, Iwan},
TITLE = {{Breton Orthographies and Dialects: The Twentieth-Century Orthography
War in Brittany}},
MAINTITLE = {{Contemporary Studies in Descriptive Linguistics}},
PUBLISHER = {Peter Lang},
ADDRESS = {Bern},
YEAR = {2008},
VOLUME = {23},
}
@PHDTHESIS{rezec,
AUTHOR = {Rezec, Oliver},
TITLE = {{Zur Struktur des deutschen Schriftsystems. Warum das Graphem nicht
drei Funktionen gleichzeitig haben kann, warum ein extup{\grapheme{a}} kein
extup{\grapheme{^^^^0251}} ist und andere Konstruktionsfehler des etablierten
Beschreibungsmodells. Ein Verbesserungsvorschlag}},
SCHOOL = {Ludwig-Maximilians-Uni\-ver\-si\-tät Munich},
YEAR = {2009},
}
@BOOK{ipa,
AUTHOR = {{IPA}},
TITLE = {{Handbook of the International Phonetic Association}},
PUBLISHER = {Cambridge University Press},
ADDRESS = {Cambridge},
YEAR = {1999},
}
@ARTICLE{grzybek,
AUTHOR = {Grzybek, Peter and Rusko, Milan},
TITLE = {{Letter, Grapheme and (Allo-)Phone Frequencies: The Case of Slovak}},
JOURNAL = {Glottotheory},
YEAR = {2009},
VOLUME = {2},
PAGES = {30--48},
}
@BOOK{guenther,
AUTHOR = {Günther, Hartmut},
TITLE = {{Schriftliche Sprache: Strukturen geschriebener Wörter und ihre Verarbeitung}},
PUBLISHER = {Niemeyer},
ADDRESS = {Tübingen},
YEAR = {1988},
}
@ARTICLE{yh95cg3,
AUTHOR = {Haralambous, Yannis},
TITLE = {{Tour du monde des ligatures}},
JOURNAL = {Cahiers GUTenberg},
YEAR = {1995},
VOLUME = {22},
PAGES = {69--70},
}
@BOOK{yh07book,
AUTHOR = {Haralambous, Yannis},
TITLE = {{Fonts \& Encodings. From Advanced Typography to Unicode and Everything in Between}},
PUBLISHER = {O'Reilly},
ADDRESS = {Sebastopol, CA},
YEAR = {2007},
}
@BOOK{wehde,
AUTHOR = {Wehde, Susanne},
TITLE = {{Typographische Kultur}},
PUBLISHER = {Max Niemeyer},
ADDRESS = {T{ü}bingen},
YEAR = {2000},
}
@ARTICLE{yh94ep2,
AUTHOR = {Haralambous, Yannis},
TITLE = {{The Traditional Arabic Typecase Extended to the Unicode Set of Glyphs}},
JOURNAL = {Electronic Publishing---Origina\-tion, Dissemination, and Design},
YEAR = {1994},
VOLUME = {8},
NUMBER = {2/3},
PAGES = {125--138},
}
@UNPUBLISHED{news,
AUTHOR = {{ABC News}},
TITLE = {{Gun Emoji Replaced with Toy Water Pistol across All Major Platforms}},
YEAR = {2018},
ADDENDUM = {\url{https://perma.cc/V8DQ-ANKN}},
}
@UNPUBLISHED{dichy2019,
AUTHOR = {Dichy, Joseph},
TITLE = {{On the Writing System of Arabic. The Semiographic Principle as Reflected
in Nasḫī Letter Shapes}},
YEAR = {in this volume},
}
@UNPUBLISHED{always,
AUTHOR = {{Stewart, Maria}},
TITLE = {{Michelle Obama Just Suggested a New Emoji to Empower Girls}},
YEAR = {2016},
ADDENDUM = {\url{https://www.huffpost.com/entry/michelle-obama-always-emoji_n_56df3feee4b03a40567a78c3?guccounter=1}},
}
@UNPUBLISHED{utr14,
AUTHOR = {Heninger, Andy},
TITLE = {{Unicode Standard Annex~14. Unicode Line Breaking Algorithm}},
YEAR = {2019},
ADDENDUM = {\url{https://www.unicode.org/reports/tr14/}},
}
@UNPUBLISHED{utr20,
AUTHOR = {Dürst, Martin and Freytag, Asmus},
TITLE = {{Unicode in XML and Other Markup Languages}},
YEAR = {2000},
ADDENDUM = {\url{https://www.w3.org/TR/2000/NOTE-unicode-xml-20001215/}},
}
@UNPUBLISHED{utr29,
AUTHOR = {Davis, Mark},
TITLE = {{Unicode Standard Annex~29. Unicode Text Segmentation}},
YEAR = {2019},
ADDENDUM = {\url{https://www.unicode.org/reports/tr29/}},
}
@UNPUBLISHED{utr9,
AUTHOR = {Davis, Mark},
TITLE = {{Unicode Standard Annex~9. Unicode Bidirectional Algorithm}},
YEAR = {2019},
ADDENDUM = {\url{https://www.unicode.org/reports/tr9/}},
}
@ARTICLE{andre,
AUTHOR = {Andr{é}, Jacques and Borghi, B.},
TITLE = {{Dynamic Fonts}},
JOURNAL = {PostScript Language Journal},
YEAR = {1990},
VOLUME = {2},
NUMBER = {3},
PAGES = {4--6},
}
@INPROCEEDINGS{bayar,
AUTHOR = {Bayar, Abdelouahad and Sami, Khalid},
EDITOR = {Al Ajeeli, Abid Thyab and Al-Bastaki, Yousif A. Latif},
TITLE = {{Towards a Dynamic Font Respecting the Arabic Calligraphy}},
BOOKTITLE = {{Handbook of Research on E-services in the Public Sector:
E-government Strategies and Advancements}},
PUBLISHER = {IGI Global},
ADDRESS = {Hershey PA},
YEAR = {2010},
PAGES = {359--379},
}
@INPROCEEDINGS{nehrlich,
AUTHOR = {Nehrlich, Thomas},
EDITOR = {Giertier, Mareike and Köppel, Rea},
TITLE = {{Phänomenologie der Ligatur. Theorie und Praxis eines Schriftelements
zwischen Letter und L{ü}cke}},
BOOKTITLE = {{Von Lettern und Lücken: zur Ordnung der Schrift im Bleisatz}},
PUBLISHER = {Wilhelm Fink},
ADDRESS = {Paderborn},
YEAR = {2012},
PAGES = {13--38},
}
@BOOK{camdic,
AUTHOR = {Brown, Keith and Miller, Jim},
TITLE = {{The Cambridge Dictionary of Linguistics}},
PUBLISHER = {Cambridge University Press},
ADDRESS = {Cambridge},
YEAR = {2013},
}
@UNPUBLISHED{utr35,
AUTHOR = {Davis, Mark},
TITLE = {{Unicode Technical Standard~35. Unicode Locale Data Markup Language}},
YEAR = {2019},
ADDENDUM = {\url{https://www.unicode.org/reports/tr35/}},
}
@UNPUBLISHED{utr51,
AUTHOR = {Davis, Mark},
TITLE = {{Unicode Technical Standard~51. Unicode Emoji}},
YEAR = {2019},
ADDENDUM = {\url{http://www.unicode.org/reports/tr51/}},
}
@UNPUBLISHED{qid-emoji,
AUTHOR = {Davis, Mark},
TITLE = {{QID Emoji} Proposal},
YEAR = {2019},
ADDENDUM = {\url{http://www.unicode.org/L2/L2019/19082r-qid-emoji.pdf}},
}
@ARTICLE{servais,
AUTHOR = {Servais, Christine and Servais, V{é}ronique},
TITLE = {{Le malentendu comme structure de la communication}},
JOURNAL = {Questons de communication},
YEAR = {2009},
VOLUME = {15},
PAGES = {21--49},
}
@BOOK{moungid,
TITLE = {{Mounged de poche français-arabe}},
PUBLISHER = {Dar el-Machreq},
ADDRESS = {Beyrouth},
YEAR = {1991},
}
@BOOK{chomsky-halle,
AUTHOR = {Chomsky, Noam and Halle, M.},
TITLE = {{The Sound Pattern of English}},
PUBLISHER = {Harper \& Row},
ADDRESS = {New York},
YEAR = {1968},
}
@BOOK{sproat,
AUTHOR = {Sproat, Richard},
TITLE = {{A Computational Theory of Writing Systems}},
PUBLISHER = {Cambridge University Press},
ADDRESS = {Cambridge},
YEAR = {2000},
}
@ARTICLE{yh94ep1,
AUTHOR = {Haralambous, Yannis},
TITLE = {{Typesetting Khmer}},
JOURNAL = {Electronic Publishing---Origina\-tion, Dissemination, and Design},
YEAR = {1994},
VOLUME = {7},
NUMBER = {4},
PAGES = {197--215},
}
@INPROCEEDINGS{yh13cicling2,
AUTHOR = {Haralambous, Yannis},
TITLE = {{New Perspectives in Sinographic Language Processing Through the
Use of Character Structure}},
BOOKTITLE = {{CICLing 2013: 14th International Conference on Intelligent Text
Processing and Computational Linguistics, Samos}},
MAINTITLE = {{Springer Lecture Notes in Computer Science}},
YEAR = {2013},
VOLUME = {7816},
PAGES = {201--217},
}
@BOOK{lotman,
AUTHOR = {Lotman, Jurij},
TITLE = {{The Structure of the Artistic Text}},
MAINTITLE = {{Michigan Slavic Contributions}},
PUBLISHER = {The University of Michigan},
ADDRESS = {Ann Arbor},
YEAR = {1977},
VOLUME = {7},
}
@BOOK{unicode12,
TITLE = {{The Unicode Standard. Version 12.0---Core Specification}},
PUBLISHER = {The Unicode Consortium},
ADDRESS = {Mountain View, CA},
YEAR = {2019},
}
@ARTICLE{yh91tb1,
AUTHOR = {Haralambous, Yannis},
TITLE = {{Typesetting Old German: Fraktur, Schwa\-bacher, Gotisch and Initials}},
JOURNAL = {TUGboat},
YEAR = {1991},
VOLUME = {12},
NUMBER = {1},
PAGES = {129--138},
}
@BOOK{anis,
AUTHOR = {Anis, Jacques},
TITLE = {{L'écriture, théorie et descriptions}},
PUBLISHER = {De Boeck},
ADDRESS = {Bruxelles},
YEAR = {1988},
}
@INPROCEEDINGS{martinet,
AUTHOR = {Martinet, Andr{é}},
TITLE = {{La double articulation du langage}},
BOOKTITLE = {{La linguistique synchronique}},
PUBLISHER = {PUF},
ADDRESS = {Paris},
YEAR = {1970},
PAGES = {7--41},
}
Yannis Haralambous
@INPROCEEDINGS{gla1-hara1,
AUTHOR = {Haralambous, Yannis and Dürst, Martin},
EDITOR = {Haralambous, Yannis},
TITLE = {Unicode from a Linguistic Point of View},
BOOKTITLE = {{Proceedings of Graphemics in the 21st Century, Brest 2018}},
PUBLISHER = {Fluxus Editions},
ADDRESS = {Brest},
YEAR = {2019},
PAGES = {167--183},
DOI = {https://doi.org/10.36824/2018-graf-hara1},
}
|