Morphological Analysis and Generation for Arabic Dialects

What it is about

The paper presents MAGEAD, a finite-state morphological analyzer and generator for Modern Standard Arabic and its dialects. Dialect morphology shares the root-and-pattern system with MSA, but orthography in dialects is not standard, and speakers mix morphemes from several varieties inside one word. The design has three levels: a lexeme with features (for example POS, person, aspect), morphemes, and the surface string. It uses a multitape finite-state model after Kiraz (2000), with five tiers: pattern and affixes, root, vocalism, phonology, and orthography. The fifth tier is new, so that inconsistent spellings can be modelled apart from sound. Templates are built from a context-free grammar of morpheme order that covers all dialects. Rewrite rules handle sound changes such as the t-to-d change in form VIII before z, d or dh. The work is in progress: no evaluation is reported, and the only test corpus available is the MSA Penn Treebank.

Ideas

• I1. Store the lexeme as the deepest key and the root only as an index field. The paper argues that meaning cannot be predicted from root and pattern (its maktab and maktaba example), so a lexicon keyed on the root would mislead. The rule belongs in languages/hbo/10-lexicon.md, and for Aramaic in languages/arc/lexicon.md.
• I2. Keep a separate orthographic tier from the phonological one. When a text is spelled in several ways, as Targumic or Zoharic Aramaic often is, the spelling and the pronunciation can be stored separately, so one analysis serves several spellings. Candidate design note for languages/arc/script-phonology.md and languages/hbo/01-script.md.
• I3. A regression suite of surface and analysis pairs, which the paper plans and which is cheap to build: a list of word forms with their expected analysis, run on each change of the rules. For Mova, take weak verbs from languages/hbo/07-weak-verbs.md and check each morphophonological rule against them.

For Mova

I1 and I2 are design decisions for languages/hbo/10-lexicon.md and languages/arc/script-phonology.md. I3 is a test suite for tools/hbo and the verb chapter languages/hbo/06-verb.md, paired with the weak-verb rules in languages/hbo/07-weak-verbs.md. No numbers are reported in the paper, so nothing here is a measured gain.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.3115/1621787.1621791

@inproceedings{habash2005morphological,
  title = {{Morphological Analysis and Generation for Arabic Dialects}},
  author = {Habash, Nizar and Rambow, Owen and Kiraz, George},
  booktitle = {Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages},
  year = {2005},
  doi = {10.3115/1621787.1621791},
  url = {https://doi.org/10.3115/1621787.1621791}
}

References

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

1. Hani Abu-Salem, Mahmoud Al-Omari, and Martha W. Evens. 1999. Stemming methodologies over individual query words for an arabic information retrieval system. J. Am. Soc. Inf. Sci., 50(6):524–529. find
2. Imad A. Al-Sughaiyer and Ibrahim A. Al-Kharashi. 2004. Arabic morphological analysis techniques: A comprehensive survey. Journal of the American Society for Information Science and Technology, 55(3):189–213. find
3. K. Beesley, T. Buckwalter, and S. Newton. 1989. Two-level finite-state analysis of Arabic morphology. In Proceedings of the Seminar on Bilingual Computing in Arabic and English, page n.p. find
4. K. Beesley. 1998. Arabic morphology using only finite-state operations. In M. Rosner, editor, Proceedings of the Workshop on Computational Approaches to Semitic Languages, pages 50–7, Montereal. find our card
5. S. Bird and T. Ellison. 1994. One-level phonology. Computational Linguistics, 20(1):55–90. find
6. Tim Buckwalter. 2004. Buckwalter Arabic morphological analyzer version 2.0. find
7. Charles F Ferguson. 1959. Diglossia. Word, 15(2):325– 340. find
8. Nizar Habash. 2004. Large scale lexeme based arabic morphological generation. In Proceedings of Traitement Automatique du Langage Naturel (TALN-04). Fez, Morocco. find
9. L. Kataja and K. Koskenniemi. 1988. Finite state description of Semitic morphology. In COLING-88: Papers Presented to the 12th International Conference on Computational Linguistics, volume 1, pages 313–15. find
10. M. Kay. 1987. Nonconcatenative finite-state morphology. In Proceedings of the Third Conference of the European Chapter of the Association for Computational Linguistics, pages 2–10. find
11. George Anton Kiraz. 2000. Multi-tiered nonlinear morphology using multi-tape finite automata: A case study on Syriac and Arabic. Computational Linguistics, 26(1):77–105. find
12. George Kiraz. 2001. Computational Nonlinear Morphology: With Emphasis on Semitic Languages. Cambridge University Press. find
13. A. Kornai. 1995. Formal Phonology. Garland Publishing. find
14. K. Koskenniemi. 1983. Two-Level Morphology. Ph.D. thesis, University of Helsinki. find
15. J. McCarthy. 1981. A prosodic theory of nonconcatenative morphology. Linguistic Inquiry, 12(3):373–418. find
16. M. Mohri, F. Pereira, and M. Riley. 1998. A rational design for a weighted finite-state transducer library. In D. Wood and S. Yu, editors, Automata Implementation, Lecture Notes in Computer Science 1436, pages 144– 58. Springer. find
17. S. Pulman and M. Hepple. 1993. A feature-based formalism for two-level phonology: a description and implementation. Computer Speech and Language, 7:333–58. find
18. R. Sproat. 1995. Lextools: Tools for finite-state linguistic analysis. Technical Report 11522-951108-10TM, Bell Laboratories. find