Elamur Research
☰
home / papers / 2014 / Arabic Dialect Identification

Arabic Dialect Identification

Written for the Research library (claude-opus-5-5) from the paper text, in our own words: the license "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" does not allow redistributing the text itself. Original — aclanthology.org/J14-1006.pdf

Summary

Arabic text is dominated by Modern Standard Arabic (MSA), the standardized written variety. The regional dialects that people actually speak are rarely written and poorly covered by existing corpora. Because all varieties share one script and much vocabulary, telling them apart automatically is difficult. The authors address this by building a dialect-rich resource from reader comments posted on Arabic online newspapers, the Arabic Online Commentary Data set (AOC). Through Amazon's Mechanical Turk, they gathered sentence-level labels for over 100,000 sentences, marking how dialectal each sentence is and which dialect it uses. The labels also reveal annotator biases, such as people over-attributing sentences to their own dialect. For classification, they train a separate language model for each Arabic variety and assign a sentence to the model that scores it best. These dialect-trained models clearly beat baselines built on much larger MSA-only data and come close to human accuracy. The resource and classifiers make it possible to collect dialectal text at scale for NLP tasks such as machine translation.

Key points

  • Resource: the Arabic Online Commentary Data set (AOC), built from newspaper reader commentary, with crowdsourced dialect annotation for more than 100,000 sentences.
  • Method: each sentence is scored with n-gram language models trained separately per Arabic variety.
  • Main result: on one task, the system reached 85.7% accuracy, compared with 88.0% for human annotators and only 66.6% for an MSA-only baseline.
  • Annotator behavior: workers tended to over-identify their own dialect.
  • Application: the classifiers were run on a Web crawl of 3.5 million pages from online Arabic newspapers to find dialectal content. Future work proposes morphological features (e.g., from BAMA, MAGEAD, ADAM, CALIMA) and covering more dialects.

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

Fields: Natural language processing

Cited by

142 papers of our library cite it (of the 140673 whose bibliographies we read); 5 of them have a page here, 137 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00169

@article{zaidan2014arabic,
  title = {{Arabic Dialect Identification}},
  author = {Zaidan, Omar F. and Callison-Burch, Chris},
  journal = {Computational Linguistics},
  year = {2014},
  doi = {10.1162/coli\_a\_00169},
  url = {https://doi.org/10.1162/coli_a_00169}
}

References

49 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abdel-Massih, Ernest T., Zaki N. Abdel-Malek, and El-Said M. Badawi. 1979. A Reference Grammar of Egyptian Arabic. Georgetown University Press. find
  2. Al-Ani, Salman H. 1970. Arabic Phonology: An Acoustical and Physiological Investigation. Mouton. find
  3. Aoun, Joseph, Elabbas Benmamoun, and Dominique Sportiche. 1994. Agreement, word order, and conjunction in some varieties of Arabic. Linguistic Inquiry, 25(2):195–220. find
  4. Badawi, El-Said and Martin Hinds. 1986. A Dictionary of Egyptian Arabic. Librairie du Liban. find
  5. Bassiouney, Reem. 2009. Arabic Sociolinguistics. Edinburgh University Press. find
  6. Biadsy, Fadi, Julia Hirschberg, and Nizar Habash. 2009. Spoken Arabic dialect identification using phonotactic modeling. In Proceedings of the EACL Workshop on Computational Approaches to Semitic Languages, pages 53–61, Athens. find
  7. Buckwalter, Tim. 2002. Buckwalter Arabic transliteration. http://www.qamus.org/transliteration.htm. ↗
  8. Buckwalter, Tim. 2004. Buckwalter Arabic morphological analyzer version 2.0. Linguistic Data Consortium, Philadelphia, PA. find
  9. Callison-Burch, Chris and Mark Dredze. 2010. Creating speech and language data with Amazon’s Mechanical Turk. In Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon’s Mechanical Turk, pages 1–12, Los Angeles, CA. find
  10. Cavnar, William B. and John M. Trenkle. 1994. N-gram-based text categorization. In Proceedings of SDAIR-94, pages 161–175, Vilnius. find
  11. Chen, Stanley F. and Joshua T. Goodman. 1998. An empirical study of smoothing techniques for language modeling. Technical Report TR-10-98, Computer Science Group, Harvard University. find
  12. Chiang, David, Mona Diab, Nizar Habash, Owen Rambow, and Safiullah Shareef. 2006. Parsing Arabic dialects. In Proceedings of EACL, pages 369–376, Trento. find our card
  13. Cowell, Mark W. 1964. A Reference Grammar of Syrian Arabic. Georgetown University Press. find
  14. Diab, Mona, Nizar Habash, Owen Rambow, Mohamed Altantawy, and Yassine Benajiba. 2010. COLABA: Arabic dialect annotation and processing. In Proceedings of the LREC Workshop on Semitic Language Processing, pages 66–74. find
  15. Dunning, T. 1994. Statistical identification of language. Technical Report MCCS 94-273, New Mexico State University. find
  16. Erwin, Wallace. 1963. A Short Reference Grammar of Iraqi Arabic. Georgetown University Press. find
  17. Fleiss, Joseph L. 1971. Measuring nominal scale agreement among many raters. Psychological Bulletin, 76(5):378–382. find
  18. Gairdner, William Henry Temple. 1925. The Phonetics of Arabic. Oxford University Press. find
  19. Garera, Nikesh and David Yarowsky. 2009. Modeling latent biographic attributes in conversational genres. In Proceedings of ACL, pages 710–718, Singapore. find
  20. Habash, Nizar. 2008. Four techniques for online handling of out-of-vocabulary words in Arabic-English statistical machine translation. In Proceedings of ACL, Short Papers, pages 57–60, Columbus, OH. find
  21. Habash, Nizar, Mona Diab, and Owen Rambow. 2012. Conventional orthography for dialectal Arabic. In Proceedings of the Language Resources and Evaluation Conference (LREC), pages 711–718, Istanbul. find
  22. Habash, Nizar, Ramy Eskander, and Abdelati Hawwari. 2012. A morphological analyzer for Egyptian Arabic. In Proceedings of the Twelfth Meeting of the Special Interest Group on Computational Morphology and Phonology, pages 1–9, Montréal. find our card
  23. Habash, Nizar and Owen Rambow. 2006. MAGEAD: A morphological analyzer and generator for the Arabic dialects. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pages 681–688, Sydney. find our card
  24. Habash, Nizar, Owen Rambow, Mona Diab, and Reem Kanjawi-Faraj. 2008. Guidelines for annotation of Arabic dialectness. In Proceedings of the LREC Workshop on HLT & NLP within the Arabic World, pages 49–53, Marrakech. find
  25. Habash, Nizar, Abdelhadi Soudi, and Tim Buckwalter. 2007. On Arabic transliteration. In Antal van den Bosch, Abdelhadi Soudi, and Günter Neumann, editors, Arabic Computational Morphology: Knowledge-based and Empirical Methods. Kluwer/Springer Publications, chapter 2. find
  26. Habash, Nizar Y. 2010. Introduction to Arabic Natural Language Processing. Morgan & Claypool. find
  27. Haeri, Niloofar. 2003. Sacred Language, Ordinary People: Dilemmas of Culture and Politics in Egypt. Palgrave Macmillan. find
  28. Holes, Clive. 2004. Modern Arabic: Structures, Functions, and Varieties. Georgetown Classics in Arabic Language and Linguistics. Georgetown University Press. find
  29. Ingham, Bruce. 1994. Najdi Arabic: Central Arabian. John Benjamins. find
  30. Kästner, Hartmut. 1981. Phonetik und Phonologie des modernen Hocharabisch. Verlag Enzyklopädie. find
  31. Landis, J. Richard and Gary G. Koch. 1977. The measurement of observer agreement for categorical data. Biometrics, 33:159–174. find
  32. Lei, Yun and John H. L. Hansen. 2011. Dialect classification via text-independent training and testing for Arabic, Spanish, and Chinese. IEEE Transactions on Audio, Speech, and Language Processing, 19(1):85–96. find
  33. Mitchell, Terence Frederick. 1990. Pronouncing Arabic. Clarendon Press. find
  34. Mohand, Tilmatine. 1999. Substrat et convergences: Le berbére et l’arabe nord-africain. Estudios de Dialectologiá Norteaafricana y andalusı́, 4:99–119. find
  35. Newman, Daniel L. 2002. The phonetic status of Arabic within the world’s languages. Antwerp Papers in Linguistics, 100:63–75. find
  36. Novotney, Scott, Rich Schwartz, and Sanjeev Khudanpur. 2011. Unsupervised Arabic dialect adaptation with self-training. In Interspeech, pages 541–544, Florence. find
  37. Řehůřek, Radim and Milan Kolkus. 2009. Language Identification on the Web: Extending the Dictionary Method, volume 5449 of Lecture Notes in Computer Science, pages 357–368. SpringerLink. find
  38. Salloum, Wael and Nizar Habash. 2011. Dialectal to standard Arabic paraphrasing to improve Arabic-English statistical machine translation. In Proceedings of the EMNLP Workshop on Algorithms and Resources for Modelling of Dialects and Language Varieties, pages 10–21, Edinburgh. find
  39. Shlonsky, Ur. 1997. Clause Structure and Word Order in Hebrew and Arabic: An Essay in Comparative Semitic Syntax. Oxford University Press. find
  40. Souter, Clive, Gavin Churcher, Judith Hayes, John Hughes, and Stephen Johnson. 1994. Natural language identification using corpus-based models. Hermes Journal of Linguistics, 13:183–203. find
  41. Suleiman, Yasir. 1994. Nationalism and the Arabic language: A historical overview. In Yasir Suleiman, editor, Arabic Sociolinguistics. Curzon Press. find
  42. Thelwall, Robin and M. Akram Sa’Adeddin. 1990. Arabic. Journal of the International Phonetic Association, 20(2):37–39. find
  43. Verma, Brijesh, Hong Lee, and John Zakos. 2009. An Automatic Intelligent Language Classifier, volume 5507 of Lecture Notes in Computer Science, pages 639–646. SpringerLink. find
  44. Versteegh, Kees. 2001. The Arabic Language. Edinburgh University Press. find
  45. Zaidan, Omar, Jason Eisner, and Christine Piatko. 2007. Using “annotator rationales” to improve machine learning for text categorization. In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference, pages 260–267, Rochester, NY. find
  46. Zaidan, Omar F. 2012. Crowdsourcing Annotation for Machine Learning in Natural Language Processing Tasks. Ph.D. thesis, Johns Hopkins University, Baltimore, MD. find
  47. Zaidan, Omar F. and Chris Callison-Burch. 2011. The Arabic Online Commentary Dataset: An annotated dataset of informal Arabic with high dialectal content. In Proceedings of ACL, pages 37–41, Portland, OR. find
  48. Zbib, Rabih, Erika Malchiodi, Jacob Devlin, David Stallard, Spyros Matsoukas, Richard Schwartz, John Makhoul, Omar F. Zaidan, and Chris Callison-Burch. 2012. Machine translation of Arabic dialects. In the 2012 Conference of the North American Chapter of the Association for Computational Linguistics, pages 49–59, Montreal. find
  49. Zissman, Marc A. 1996. Comparison of four approaches to automatic language identification of telephone speech. IEEE Transactions on Speech and Audio Processing, 4(1):31–44. find