Elamur Research⌕
☰
home / papers / 2011 / Arabic and computer-aided translation: an integrated approach

Arabic and computer-aided translation: an integrated approach

Paper · 2011 · Barbara Quaranta

Summary

This paper asks why translators of Arabic rarely use computer-aided translation (CAT) tools, and what goes wrong when they do. These tools were designed around Western languages. The author ran an experiment with SDL Trados 2007, translating two Arabic preliminary sales contracts into English. One was a blank template and the other a real signed agreement. A short survey of Arabic translators guided which texts to choose.

Two families of failure appeared:

  • Formatting: fonts, sparse punctuation, and symbols used in place of punctuation broke segmentation.
  • Morphology: attached prefixes, suffixes and infixes, plus optional diacritics, stopped translation-memory and termbase lookups from matching.

The author proposes a set of workarounds:

  • macros that insert punctuation,
  • an Arabic spelling corrector,
  • undiacritised memories,
  • tuned fuzzy-match thresholds,
  • a custom tool that expands each term with every possible prefix before termbase import.

The paper then reviews Arabic computational linguistics. It argues that morphological analysis, already used in machine translation, should be built into CAT tools. This would make the software properly internationalised rather than patched from outside.

Key points

  • Tool and test data: SDL Trados 2007 was tested on two Arabic preliminary sales contracts translated into English. Segmentation, translation memories, termbases and fuzzy matching were all examined.
  • Segmentation fix: Sentences often lack punctuation, so default segmentation rules fail. Substitution macros replaced recurring expressions and symbols that act like punctuation with real punctuation marks. Orthographic variants were handled with the Microsoft Office Multilingual User Interface Pack.
  • Diacritics: The software treats diacritics as ordinary characters, so vocalised and plain forms of a word do not match. The suggested mitigations are:
    • store memories and termbases without diacritics,
    • add vocalised variants through Multiple translation options,
    • lower the fuzzy-match threshold.
  • Prefix expansion tool: An Access application (Visual Basic/SQL) produces an Excel sheet listing every prefixed form of a term. MultiTerm Convert turns it into XML for a MultiTerm termbase. The tool was built with research at Cairo University and a morphological analysis by an R.D.I. researcher.
  • Remaining limitation: Suffixes, such as regular plurals, are only partly caught by lowering fuzzy match. Short words with long suffixes still fail because matching is percentage-based. The paper cites Farghaly (2010), Sawaf (2010) and Tymoczko (1998).

Interesting ideas

  • I1. Before splitting sentences, rewrite recurring phrases and symbols that act as boundaries into explicit punctuation, so a generic segmenter works on poorly punctuated text.
  • I2. Instead of making the matcher smarter, enlarge the lexicon by generating every affixed surface form of a term ahead of time, so plain exact lookup succeeds.
  • I3. Optional marks such as diacritics should not count as identity-changing characters; keep one normalised key and attach the marked variants to it.
  • I4. Character-percentage similarity breaks down when affixes are long relative to the stem, so similarity should be measured on morphological units, not raw strings.
  • I5. Ask practitioners which documents cause them trouble before picking test material, so the evaluation targets real failure cases.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (tokens): A pre-segmentation normaliser could map list markers, dashes or connective formulas in legal or informal English to sentence breaks, and log each rewrite so the change stays explainable.
  • I2 (world): Ontology and knowledge-graph entries from WordNet or Wikidata could be pre-expanded with inflected and possessive forms, keeping each variant linked to its lemma for traceable entity matching.
  • I3 (tokens): The tokenizer could hold a stripped key for accents, curly quotes and ligatures alongside the original string, so lookups succeed while the surface text is preserved.
  • I4 (learn): Evaluation of matching and repair rules could report results by word length or affix ratio, as a control that exposes string-similarity shortcuts.
  • I5 (answer): Test sets for the readers could be seeded from teachers' reports of question types students stumble on, rather than only from convenient corpora.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

🧭 Topics 1Research subjects and languages the work is about.Semitic languages · 1,484 works

Cite

Cite as Barbara Quaranta. 2011. Arabic and computer-aided translation: an integrated approach. Proceedings of Translating and the Computer 33.

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{quaranta2011arabic,
  title = {{Arabic and computer-aided translation: an integrated approach}},
  author = {Barbara Quaranta},
  booktitle = {Proceedings of Translating and the Computer 33},
  year = {2011},
  url = {https://aclanthology.org/2011.tc-1.14/}
}

References

91 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Attia, M. (2000). A large-scale computational processor of the Arabic morphology, and applications. Giza: Cairo University. find
  2. Austermuhl F., (2001). Electronic Tools for Translators (Translation Practices Explained). Manchester: St. Jerome Publishing. find
  3. Baker, M. (1992). In Other Words: A Coursebook on Translation. London/New York: Routledge. find
  4. Barber, B. (2000). Jihad vs. McWorld: Globalization and the Challenges of a New Century: A Reader. Bloomington, Indiana: Indiana University Press. find
  5. Bell, R. T. (1991). Translation and Translating: Theory and Practice. London/New York: Longman. find
  6. Bishop, M. (1998). How to Build a Successful International Web Site. Corious Group. find
  7. Bowker, L., M. Cronin, D. Kenny & Pearson eds. (1998). Unity in diversity? Current trends in translation studies. Manchester: St. Jerome publishing. find
  8. Buckwalter, T. (2004). “Issues in Arabic Orthography and Morphology Analysis”, proceedings of the Workshop on Computational Approaches to Arabic Script-based Languages, August 28, 2004. Geneva.
  9. Campbell, G. (2000). Compendium of the World's Languages. New York: Routledge. find
  10. Campbell, G. (1997). Concise Compendium of the World's Languages. New York: Routledge. ethnocentrism related to translation Campbell, G. (1997). Handbook of Scripts and Alphabets. New York: Routledge. find
  11. Carmel, E. (1999). Global Software Teams: Collaborating Across Borders and Time Zones. Upper Saddle River, NJ: Prentice Hall PTR. find
  12. Carrol, S. (2000). “Introducing the TRADOS Workflow Development” in Translating and the computer 22. Aslib proceedings. find
  13. Ciola, B., Coluccia, S., Maganzi Giorni D´Angiò, F. & F. Mayer (2000). Atti del Seminario: Traduzione e computer: le nuove tecnologie nella traduzione assistita. Bolzano 30 giugno - 1 luglio. find
  14. Ciola B. e F. Mayer a cura di (1999), Traduzione assistita, in Atti del Seminario Terminologia e Traduzione assistita, AITI Sez. Veneto Trentino-Alto Adige. find
  15. Comrie, B. (1990). The World's Major Languages. Oxford: Oxford University Press. find
  16. Comrie, B., S. Matthews, & M. Polinsky, eds. (1996). The Atlas of Languages: The Origin and Development of Languages throughout the World. New York: Checkmark Books. find
  17. Daniels, P. T. & W. Bright (eds.). (1996). The World's Writing Systems. Oxford: Oxford University Press. find
  18. Daniels, J. L. & N. C. Daniels. (1993). Global Vision: Building New Models for the Corporation of the Future. New York: McGraw-Hill. find
  19. Del Galdo, E. & J. Nielsen. (1996). International User Interfaces. New York: John Wiley and Sons. find
  20. Dennet, G. (1995). Translation Memory: Concept, products, impact and prospects. London: South Bank University. find
  21. De Palma, D.A. (2002). Business Without Borders: A Strategic Guide to Global Marketing. New York: John Wiley and Sons. find
  22. Digital Equipment Corporation. (1991). Digital Guide to Developing International Software. Digital. Dr. find
  23. International (ed.). (2002). Developing International Software, 2nd edition. Redmond, WA: Microsoft Press. Eid, M. et. find
  24. Al. (2006). Encyclopaedia of Arabic Language and Linguistics. Boston: Brill. find
  25. Esselink, B. (2000). A Practical Guide to Localization, Amsterdam: John Benjamins Publishing Co. find
  26. Erard, M. (2004). “Translation in the age of terror”. Technology Review, 107: issue 2. find
  27. Farghaly, A. (2010), edited by, Arabic Computational Linguistics, CSLI Studies in Computational Linguistics, CSLI Publications, Stanford, California. find
  28. Fromkin, V. & R. Rodman. (1998). An Introduction to Language. Forth Worth: Harcourt College Publishers. find
  29. Gaspari, F. (1999). The role of MT and MAT for the professional translator. Forlì: Scuola Superiore di Lingue Moderne per Interpreti e Traduttori. find
  30. Gillam, R. (2002). Unicode Demystified: A Practical Programmer's Guide to the Encoding Standard. Boston: Addison Wesley Professional. find
  31. Gotti, M. (1991). I linguaggi specialistici. Firenze: La Nuova Italia Editrice. find
  32. Hall, P.A.V. & R. Hudson. (1997). Software Without Frontiers-A multiplatform, multicultural, multination approach. New York: John Wiley and Sons. find
  33. Heyn, M. (1998). “Translation Memories: Insights and Prospects” in L. Bowker, M. Cronin, D. find
  34. Khan, G. M. (2001). Arabic Script. New York: Abbeville Press. find
  35. Hofstede, G. (1997). Cultures and Organizations : Software of the Mind; Intercultural Cooperation and Its Importance for Survival. Revised edition. New York: McGraw-Hill. find
  36. Hofstede, G. (1984). Cultures Consequences: International Differences in Work-Related Values. Oxford: Paperback Abridged edition. find
  37. Hoft, N. (1995). International Technical Communication. New York: John Wiley & Sons. find
  38. Hutchins, J. (2000). The Early Years of Machine Translation. Amsterdam, Philadelphia: John Benjamins Publishing Co. find
  39. Hutchins, J. (1998). “The Origins of the Translator's Workstation”. Machine Translation. 13: 287-305. ↗
  40. Kano, N. (1995). Developing International Software. Redmond: Microsoft Press. find
  41. Karolak, D. W. (1998). Global Software Development: Managing Virtual Teams and Environment. New Brunswick: The Computer Society. find
  42. King, M. ed. (1987). Machine Translation Today: The State of the Art. Proceedings of the Third Lugano Tutorial. 2-7 April 1984. Edinburgh: Edinburgh University Press. find
  43. Kugler, M., K. Ahmad & G. Thurmair (Eds.) (1995). Translator's Workbench: Tools and Terminology for Translation and Text Processing. Berlin: Springer Verlag. find
  44. Ladikoff Guasto, C. (2002). Ahlan. Grammatica araba didattico-comunicativa. Roma: Carocci editore. find
  45. Lesina, B., (1998). Il nuovo manuale di stile. Bologna: Zanichelli. find
  46. Luong, Tuoc V., S. H. James Lok, D. J. Taylor & K. Driscoll. (1995) Internationalization - Developing Software for Global Markets. New York: John Wiley & Sons. find
  47. Macklovitch E. (2000). “Two Types of Translation Memory” in Translating and the Computer 22. find
  48. Aslib proceedings (2000). find
  49. Manca, A. (1999). Grammatica (teorico-pratica) di arabo letterario moderno, Associazione nazionale di amicizia e di cooperazione italo-araba. Roma: Anissa. find
  50. Martin O'Donnell, S. (1994). Programming for the World: A Guide to Internationalization. N.J.: Prentice Hall. find
  51. Melby, A. (1985). “Machine Translation vs. Translator Aids: A False Dichotomy” in S. Williams (1985). 45-53. find
  52. Melby, A. (1987a). “Creating an Environment for the Translator” in M. King (1987). 124-132. find
  53. Melby, A (1987b). “On human-machine interaction in translation” in S. Nirenburg (1987). 145-154. find
  54. Melby, A. (1992). “The translator workstation” in J. Newton. (1992). 147-165. find
  55. Milo, T. (2002). “Authentic Arabic: A case Study”. 20th International Unicode Conference. Washington, DC. find
  56. Muzii, L. (2001). “Scegliere gli strumenti CAT. Criteri di valutazione” dispensa del Seminario di introduzione all'uso di strumenti per la traduzione assistita: Déjà Vu, Star Transit e Trados Freelance Edition. find
  57. Roma 10-11 febbraio 2001. A.I.T.I Sezione Lazio. find
  58. Muzii, L. (1995). La redazione dei documenti tecnici. Milano: Franco Angeli. find
  59. Newton, J. ed. (1992). Computers in translation. A practical appraisal. London: Routledge. find
  60. Nirenburg, S. ed. (1987). Machine Translation: theoretical and methodological issues. Cambridge: Cambridge University Press. find
  61. O' Brien, S. (1998). “Practical Experience of Computer-Aided Translation Tools in the Software Localization Industry” in Bowker, L., Cronin M., Kenny, D. & J. Pearson (1998). 115-122. find
  62. Osimo, B. (2004). Manuale del traduttore. Milano: Hoepli. find
  63. Osimo, B. (2001). Traduzione e nuove tecnologie. Milano: Hoepli. find
  64. Ott, C. (1999). Global Solutions for Multilingual Applications. New York: John Wiley & Sons. find
  65. Pinker, S. (2000). The Language Instinct: How the Mind Creates Language. New York: Harper Perennial Library. find
  66. Rosen, R. (2000). Global literacies: Lessons on Business Leadership ond National Cultures: A Landmark Study of CEOs from 28 Countries. New York: Simon & Schuster. find
  67. Sager, J. C. (1993). Language Engineering and Translation: Consequences of Automation. John Benjamins Publishing Co. find
  68. Sager, J.C. (1979). “Multilingual Communication“ in B. M. Snell (1979). 1-25. find
  69. Scarpa F. (2001). La traduzione specializzata. Milano: Hoepli. find
  70. Schmitt, D. A. (1999). International Programming for Microsoft Windows: Guidelines for Software Localization with Examples in Microsoft Visual C (Dv-Mps Programming).Redmond: Microsoft Press. find
  71. Schütz, J. (1998). “Multilingual Human Language Technology in Automotive Documentation Workflows” in Translating and the computer 20. Aslib proceedings (1998). find
  72. Snell, B.M. ed. (1979). “Translating and the Computer”. Proceedings of a seminar, London, 14th November, 1978. Amsterdam: North-Holland. find
  73. Sprung, R. (2000). Translating into Success. Amsterdam,Philadelphia: John Benjamins Publishing Co. find
  74. Stonehouse, G., J. Hamill, D. Campbell & T. Purdie. (1998). Global and Transnational Business: Strategy and Management. New York: John Wiley & Sons. find
  75. Sobrero A.A. (1993). “Lingue speciali” in A. A. Sobrero (1993). 237-277. find
  76. Sobrero A.A. a cura di (1993). Introduzione all'italiano contemporaneo. La variazione gli usi. Roma: Laterza. find
  77. SyNTHEMA (2000). “Progettazione, sviluppo e integrazione di software di Traduzione automatica e Traduzione assistita”, dispensa del Convegno internazionale A.I.T.I Multimedia 2000, Capomulini (CT) 6-8 giugno 2000. find
  78. Taylor, D. (1992). Global Software: Developing Applications for the International Market. Heidelberg: Springer Verlag. find
  79. Traini, R. (1999). Vocabolario arabo-italiano, Roma: Istituto per l’Oriente. Translating and the Computer 20. Papers from the Aslib conference held on 12 & 13 November 1998. London: Aslib. find
  80. Trompenaars, A. & C. Hampden-Turner, F. Trompenaars. (1998). Riding the Waves of Culture: Understanding Cultural Diversity in Global Business. Chicago: Irwin Professional Pub. find
  81. Tuthill, B. and D. Smallberg. (1997). Creating Worldwide Software. (2nd edition). Sun Press-Prentice Hall. find
  82. Tymoczko, M., (1998), Computerized Corpora and the Future of Translation Studies, in Meta: Translators' Journal, vol. 43, n° 4, 1998. find
  83. Uren, E. et al. (1993). An Introduction to Software Internationalization and Localization. New York: Van Nostrand Reinhold. find
  84. van Hoof, B. Keck, R. Mazer, M. Kugler & C. Menzel (1995). “Translation Memory”. In M. find
  85. Kugler, K. Ahmad & G. Thurmair eds. (1995). 83-99. find
  86. Watkins, J. (2001). The Guide to Translation and Localization: Preparing Products for the Global Marketplace. Portland, Oregon: Lingo Systems. find
  87. Williams, S. ed. (1982). “Humans and machine”, proceedings of the 4th Delaware Symposium on Language Studies, 1982. Norwood, N.J.: Ablex Pub. Corp. find
  88. Wright, S. E. & G. Budin. (1997/2001). The Handbook of Terminology Management. Amsterdam/Philadelphia: John Benjamins Publishing Co . find
  89. Wright, S. E. & R.A. Strehlow. (1995). Harmonizing Terminology for Translation and Information Retrieval: Theory and Practice, ASTM (STP 1223). Philadelphia: ASTM. find
  90. Zawaydeh, B. (1999). The Phonetics and Phonology of Gutturals in Arabic. Ph.D. Dissertation. Indiana University. Webography Assénat-Falcone, S. (29/11/2000). More Translation Memory Tools (not many more, but good ones). http://www.accurapid.com/journal/12TM.htm ↗
  91. Assénat-Falcone, S. (29/03/2001). Translation Aid Software. Four Translation Memory Programs Reviewed. http://www.accurapid.com/journal/03TM2.htm Benis, ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/quaranta-2011-arabic-computer-aided-translation-integrated/