Elamur Research⌕
☰
home / papers / 2019 / Verbs in Egyptian Arabic: a case for register variation

Verbs in Egyptian Arabic: a case for register variation

Paper · 2019 · Michael Grant White and Deryle W. Lonsdale

Summary

Studying register in Egyptian Arabic (EA) has been hard because no annotated corpus covers both its spoken and written forms. The authors build CALM (Corpus al-Logha al-Musriya), a corpus of about two million EA words. It combines hand-made transcripts of Egyptian films and scripted TV shows with dialectal internet texts. Verbs were tagged automatically with MADAMIRA and then fully checked by hand. Using this layer, the authors compare a Movies subcorpus and a Blogs subcorpus. They look at verb frequency, verbal categories (perfect, imperfect, habitual, future, imperatives) and lexical diversity. The two registers differ significantly, and the pattern fits earlier multidimensional register research on other languages.

A second finding is about method. Statistics from the uncorrected tagger output would have supported almost the same conclusions as the hand-corrected gold data, even though the raw counts shifted. The work gives EA a reusable resource and a first empirical baseline for register study. It also shows how far automatic annotation can be trusted for corpus-level questions.

Key points

  • CALM contains three parts:
    • transcripts of 65 movies (655,858 tokens)
    • 88 scripted TV programs (396,734 tokens)
    • internet texts (1,092,442 tokens)
  • Someone whose first language is Egyptian Arabic checked each transcript. An additional reviewer then went over the material to test whether those initial checks had really found every error.
  • Blog texts were gathered in two ways:
    • Bing/Google searches seeded with frequent EA-specific n-grams, chosen to limit dialect mixing
    • the BootCat web-to-corpus pipeline
  • Verb diversity (types relative to verb count) was higher in Blogs than in Movies:
    • gold data: 7.53 vs 5.88
    • raw MADAMIRA output: 10.08 vs 7.44, which inflates the gap
  • MADAMIRA's typical errors:
    • It over-counted PERFECT and IMPERFECT, mostly by tagging personal names as verbs. Arabic script has no capitals to separate them.
    • In Movies, 17 word forms caused 37.6% of verb false positives.
    • It under-counted IMPERATIVE (about −36% to −38%) and HABITUAL.
    • A Python post-processor aimed at its most frequent errors raised precision from 0.922 to 0.944.

Interesting ideas

  • I1. Judge an automatic tagger by whether the study's statistical conclusions stay the same after hand-correction, not only by its accuracy, since a noisy annotator can still be reliable for aggregate questions.
  • I2. Write a targeted post-processing fixer while manually correcting the data, since the most frequent repeated errors become obvious and a small rule layer removes a measurable share of them.
  • I3. Rank false positives by word form; here a handful of names produced over a third of the verb errors, which shows that a short list can fix much of a tagger's problem.
  • I4. Add a second reviewer to measure how reliable the first reviewers are, rather than assuming human checking is error-free.
  • I5. Normalize lexical diversity both per verb and per word, so that one register's differing verb density does not skew the comparison.

For Mova

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

  • I1 (learn): Silver-data evaluation could check whether downstream measurements, such as frame or verb-class distributions, change significantly between silver and gold samples, not only LAS.
  • I2 (learn): Self-induced repair rules could be mined from the highest-frequency correction patterns, then tested to see whether their precision gain holds on held-out text.
  • I3 (tokens): A per-word-form error report for the tagger would show where name gazetteers or casing-independent cues are needed, e.g. for lowercased, headline or all-caps English input.
  • I4 (learn): When LLM-teacher tiers or human checks build gold sets, a secondary audit pass could estimate each checker's miss rate and weight their labels accordingly.
  • I5 (answer): When comparing genres of test texts (fables vs. school-course texts), Mova could report both normalizations to tell vocabulary richness apart from how often a part of speech occurs.

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, topics and concepts

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

🧭 Topics 1Research subjects and languages the work is about.Semitic languages · 3,066 works

Cite

Cite as Michael Grant White and Deryle W. Lonsdale. 2019. Verbs in Egyptian Arabic: a case for register variation. Proceedings of the 3rd Workshop on Arabic Corpus Linguistics.

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

@inproceedings{white2019verbs,
  title = {{Verbs in Egyptian Arabic: a case for register variation}},
  author = {Michael Grant White and Deryle W. Lonsdale},
  booktitle = {Proceedings of the 3rd Workshop on Arabic Corpus Linguistics},
  year = {2019},
  url = {https://aclanthology.org/W19-5608/}
}

References

56 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ernest T. Abdel-Massih, Zaki N. Abdel-Malek, and El-Said Badawi. 2009. A Reference Grammar of Egyptian Arabic. Georgetown University Press, Washington D.C. find
  2. Hitham Abo Bakr, Khaled Shaalan, and Ibrahim Ziedan. 2008. A Hybrid Approach For Converting Written Egyptian Colloquial Dialect Into Diacritized Arabic. In The 6th International Conference on Informatics and Systems (INFOSYS 2008). find
  3. Rania Al-Sabbagh and Roxana Girju. 2012a. A Supervised POS Tagger for Written Arabic Social Networking Corpora. In Proceedings of the Conference on Natural Language Processing (KONVENS), pages 39–52. find
  4. Rania Al-Sabbagh and Roxana Girju. 2012b. YADC: Yet another Dialectal Arabic Corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC), pages 2882–2889. find
  5. Jawharah Alasmari, E. Atwell, and J. Watson. 2017. Using the Quranic Arabic Corpus for Comparative Analysis of the Arabic and English Verb Systems. International Journal on Islamic Applications in Computer Science and Technology, 5. find
  6. Douglas Biber. 1999. Longman Grammar of Spoken and Written English. Harlow, England. find
  7. Douglas Biber. 2006. University Language: A Corpus-based Study of Spoken and Written Registers. John Benjamins, Philadelphia. find
  8. Douglas Biber and Susan Conrad. 2001. Register Variation: A Corpus Approach. In The Handbook of Discourse Analysis. Blackwell Publishers, Massachusetts. find
  9. Abdullah Alfaifi and Eric Atwell. 2015. Arabic learner corpus. ↗
  10. Douglas Biber, Mark Davies, James K. Jones, and Nicole Tracy-Ventura. 2006. Spoken and Written Register Variation in Spanish: A Multidimensional Analysis. Corpora, 1(1):1–37. find
  11. Ahmed Ali, Stephan Vogel, and Steve Renals. 2017. Speech recognition challenge in the wild: Arabic MGB-3. In 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 316–322.
  12. Douglas Biber, Jesse Egbert, and Mark Davies. 2015. Exploring the Composition of the Searchable Web: A Corpus-Based Taxonomy of Web Registers. Corpora, 10(1):11–45. ↗
  13. Marwah Alian and Arafat Awajan. 2018. Arabic Tag Sets. In Proceedings of SAI Intelligent Systems Conference, pages 592–606. Springer. find
  14. Khalid Almeman and Mark Lee. 2013. Automatic Building of Arabic Multi Dialect Text Corpora by Bootstrapping Dialect Words. In Proceedings of 1st International Conference on Communications, Signal Processing, and their Applications (ICCSPA), pages 1–6, Sharjah, UAE. Institute of Electrical and Electronics Engineers (IEEE). find
  15. Mohamed Al-Badrashiny Arfath Pasha, Mona T. Diab, and Ahmed El Kholy. 2014. MADAMIRA: A Fast, Comprehensive Tool for Morphological Analysis and Disambiguation of Arabic. In Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC).
  16. Marco Baroni and Silvia Bernardini. 2004. Boot-CaT: Bootstrapping Corpora and Terms from the Web. In Proceedings of the 4th Langauge Resources Evaluations Conference (LREC), page 1313. find
  17. Randell Bentley. 2015. Conditional Senteces in Egyptian Colloquial Arabic and Modern Standard Arabic: A Corpus Study. Master’s thesis, Brigham Young University. find
  18. Douglas Biber. 1993. Representativeness in Corpus Design. Literary and Linguistic Computing, 8(4):2430–257. ↗
  19. Marc Brysbaert and Boris New. 2009. Moving beyond Kučera and Francis: A Critical Evaluation of Current Word Frequency Norms and The Introduction of a New And Improved Word Frequency Measure For American English. Behavior Research Methods, 41(4):977–990. ↗
  20. Tim Buckwalter and Dilworth Parkinson. 2011. A Frequency Dictionary of Arabic: Core Vocabulary for Learners. Routledge, New York. find
  21. Alexandra Canavan, George Zipperlen, and David Graff. 1997. CALLHOME Egyptian Arabic Speech. Linguistic Data Consortium Web Download, LDC97S45. Philadelphia, PA. find
  22. Leon Derczynski, Alan Ritter, Sam Clark, and Kalina Bontcheva. 2013. Twitter Part-of-speech Tagging for All: Overcoming Sparse and Noisy Data. In Proceedings of the International Conference Recent Advances in Natural Language Processing (RANLP), pages 198–206.
  23. Mona Diab, Kadri Hacioǧlu, and Daniel Jurafsky. 2004. Automatic Tagging Of Arabic Text: From Raw Text To Base Phrase Chunks. In Proceedings of HLT-NAACL 2004: Short papers, pages 149–152. Association for Computational Linguistics.
  24. James Dickins. 2017. The Pervasiveness of Coordination in Arabic, with Reference to ArabicgtEnglish Translation. Languages in Contrast, 17(2):229–254. find
  25. Kevin Duh and Katrin Kirchhoff. 2005. POS Tagging Of Dialectal Arabic: A Minimally Supervised Approach. In Proceedings of the acl Workshop on Computational Approaches to Semitic Languages, pages 55–62. Association for Computational Linguistics.
  26. Ted Dunning. 1993. Accurate Methods for the Statistics of Surprise and Coincidence. Computational Linguistics, 19(1):61–74. Formal Features. American University in Cairo, Egypt.
  27. Susan Hunston. 2002. Corpora in Applied Linguistics. Cambridge University Press, Cambridge. ↗
  28. Mona Hussein. 2016. Propositional and Non-Propositional Functions of /Keda/ in the Language of Egyptian Film. American University in Cairo, Egypt. find
  29. Abbas El-Tonsi. 1982. Egyptian Colloquial Arabic: A Structure Review, volume 1. American University In Cairo, Cairo, Egypt. find
  30. Ahmad Ismail. 2015. ṭab asta’zen ana ba’a: A corpus-based Study of Three Discourse Markers in Egyptian Film Language. American University in Cairo, Egypt. find
  31. Ahmed Fakhri. 2009. Rhetorical variation in Arabic academic discourse: Humanities versus law. Journal of Pragmatics, 41(2):306–324. ↗
  32. Barbra Johnstone. 2008. Discourse Analysis. Blackwell, Malden, MA. find
  33. Charles A. Ferguson. 1983. Sports announcer talk: Syntactic aspects of register variation. Language in Society, 12(2):153–172. ↗
  34. Pierfranca Forchini. 2012. Movie Language Revisited: Evidence from Multi-Dimensional Analysis and Corpora. Peter Lang, Bern. find
  35. Eric Friginal. 2009. Language of Outsourced Call Centers: A Corpus-based Study of Cross-cultural Interaction. John Benjamins, Philadelphia. find
  36. Sandra Kübler and Heike Zinsmeister. 2015. Corpus Linguistics and Linguistically Annotated Corpora. Bloomsbury, New York. find
  37. Mohamed Maamouri, Ann Bies, Seth Kulick, Michael Ciul, Nizar Habash, and Ramy Eskander. 2014. Developing an Egyptian Arabic Treebank: Impact of Dialectal Morphology on Annotation and Tool Development. In Proceedings of LREC, pages 2348–2354. find
  38. Yousef Maati. 2008. ɦʌsʌn wi murʔosʕ. Al-daar Al-Masriya Al-lubnaniya, Cairo, Egypt. find
  39. Stefan Th. Gries. 2006. Exploring variability within and between corpora: some methodological considerations. Corpora, 1(2):109–151. ↗
  40. Hamdi A. Qafisheh. 1992. Yemeni Arabic Reference Grammar. Dunwoody Press, Kensington, MD. find
  41. Nizar Habash, 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 (SIG-PHON), pages 1–9. Association for Computational Linguistics.
  42. Paul Rayson and Roger Garside. 2000. Comparing corpora using frequency profiling. In Proceedings of the workshop on Comparing corpora, volume 9, pages 1–6. Association for Computational Linguistics. find
  43. Nizar Y. Habash and Owen C. Rambow. 2006. MAGEAD: A Morphological Analyzer And Generator For The Arabic Dialects. ↗
  44. Gadalla Hassan. 2000. Comparative Morphology of Standard and Egyptian Arabic. LINCOM EUROPA. find
  45. David Henen. 2018. “ya” between Vocative and Non-Vocative Use in Egyptian Film Language A Corpus Analysis: Pragmatic Functions and Karin C. Ryding. 2005. A Reference Grammar of Modern Standard Arabic. Cambridge University Press, Cambridge, England. find
  46. Karin C. Ryding. 2006. Teaching Arabic in the United States. In Handbook for Teaching Arabic Language Professionals in the 21st Century, pages 13–20. Routledge, New York. find
  47. Mukhtar Sayed. 2018. maʕleš maʕleš: A CORPUS-BASED STUDY ON THE DIS-COURSE MARKER maʕleš. American University in Cairo, Egypt. find
  48. Serge Sharoff. 2006. Creating general-purpose corpora using automated search engine queries. In Baroni and Bernardini, editors, WaCky! Working papers on the Web as Corpus, pages 63–98. Gedit. find
  49. John Sinclair. 2004. Corpus Creation. In Geoffrey Sampson and Diana McCarthy, editors, Corpus Linguistics: Readings in a Widening Discipline, pages 78–84. Continuum, New York. find
  50. Shelly Staples. 2016. Identifying Linguistic Features of Medical Interactions: A Register Analysis. Talking at Work. Palgrave Macmillan, London. ↗
  51. Rianne Tamis and Janet Persson, editors. 2013. Sudanese Arabic-English; English-Sudanese Arabic: A Concise Dictionary. SIL International. find
  52. Christopher John Taylor. 2004. The Language of Film: Corpora and Statistics in the Search for Authenticity. Notting Hill (1998)-A Case Study. Miscelánea, pages 71–86. find
  53. Wolfgang Teubert. 2005. My Version of Corpus Linguistics. International Journal of Corpus Linguistics, 10(1):1–13. ↗
  54. Huihsin Tseng, Daniel Jurafsky, and Christopher Manning. 2005. Morphological features help POS tagging of unknown words across language varieties. In Proceedings of the Fourth SIGHAN Workshop on Chinese Language Processing. find
  55. Michael Grant White. 2019, forthcoming. Verb usage in Egyptian Arabic: a case for register variation. Master’s thesis, Brigham Young University. find
  56. Andrew Wilson. 2013. Embracing Bayes Factors for key item analysis in corpus linguistics. In M. Bieswanger and A. Koll-Stobbe, editors, New Approaches To The Study Of Linguistic Variability, pages 3–9. Peter Lang, Frankfurt. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/white-2019-verbs-egyptian-arabic-case-register/