📄 Morphological Synthesizer for Ge'ez Language: Addressing Morphological Complexity and Resource Limitations

What it is about

A rule-based synthesizer generates Ge'ez verb forms in Ge'ez script from infinitive stems, using two-level morphology. It forms five stems per tense-mood, then the TAM forms, then person-number-gender suffixes and object suffixes. A stem classifier marks a verb irregular when it contains a guttural (ሀ ሐ ኀ አ ዐ) or a semi-vowel (የ ወ). The test set is 1,102 sample verbs taken from grammar books and the Bible, not a held-out corpus. Experts checked the output by error counting: 99.6% for regular verbs (7,577 words), 96.6% for irregular verbs (19,290 words), 97.4% overall, against 96.28% for an earlier Afan Oromo verb system. The error analysis names exceptional stems, concatenation exceptions and missing rules. The figures are not internally consistent: 8 errors in 7,577 words is about 99.9%, not 99.6%, and 8 + 661 is 669, not the stated 668. Treat the split with care.

Ideas

• I1. Test the letter-class rule on data. The paper calls a verb irregular when it contains a guttural or semi-vowel. Check this on MACULA Hebrew verbs: how many forms change class under the rule, and do the weak-root verbs fall into the irregular set? See languages/hbo/07-weak-verbs.md.
• I2. Split every score by class, as the paper does for regular and irregular verbs, and state the mix of the test set. A single overall figure depends on that mix, as the authors themselves say.
• I3. Compile boundary changes to a transducer. The boundary handler (suffixes change the last letter of stems ending in ቀ, ከ or ገ) is a finite-state rule. The lex and pre tables in tools/hbo could compile the same kind of rule to an FST, with the paper's error list kept as a regression set.

For Mova

I1 is a class test on languages/hbo/07-weak-verbs.md with MACULA data. I2 is the reporting format for verb tests in tools/macula compare. I3 is for tools/hbo (segmenter tables).

Cite

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

@inproceedings{gidey2024morphological,
  title = {{Morphological Synthesizer for Ge'ez Language: Addressing Morphological Complexity and Resource Limitations}},
  author = {Gidey, Gebrearegawi Gebremariam and Teklehaymanot, Hailay Kidu and Atsbha, Gebregewergs Mezgebe},
  booktitle = {Proceedings of the Fifth Workshop on Resources for African Indigenous Languages @ LREC-COLING 2024},
  year = {2024},
  url = {https://aclanthology.org/2024.rail-1.11/}
}

References

35 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Yitayal Abate. 2014. Morphological analysis of ge’ez verbs using memory based learning. find
2. A. Abebe. 2010. Automatic morphological synthesizer for afaan oromoo. A thesis Submitted to School of Graduate Studies of addis ababa University in Partial fulfillment for degree masters of Science in Computer Science. find
3. Abebe Abeshu. 2013. Analysis of rule based approach for afan oromo automatic morphological synthesizer. Science, Technology and Arts Research Journal, 2(4):94–97. ↗
4. Abebe Belay Adege and Yibeltal Chanie Mannie. 2017. Designing a Stemmer for Ge’ez Text Using Rule based Approach. LAP LAMBERT Academic Publishing. find
5. James Allen. 1995. Natural language understanding. Benjamin-Cummings Publishing Co., Inc. Kenneth R Beesley and Lauri Karttunen. Finite-state morphology: Xerox tools and techniques. CSLI, Stanford, pages 359–375. find
6. Wendy Laura Belcher. 2012. Abyssinia’s Samuel Johnson: Ethiopian Thought in the Making of an English Author. OUP USA. find
7. Walter Bisang, Hans Henrich Hock, Werner Winter, Jost Gippert, Nikolaus P Himmelmann, and Ulrike Mosel. 2006. Essentials of language documentation. Mouton de Gruyter. find
8. Berihu Weldegiorgis Desta. 2010. Design and Implementation of Automatic Morphological Analyzer for Ge’ez Verbs. Ph.D. thesis, Addis Ababa University. find
9. August Dillmann and Carl Bezold. 2003. Ethiopic grammar. Wipf and Stock Publishers. find
10. Sasi Raja Sekhar Dokkara, Suresh Varma Penumathsa, and Somayajulu G Sripada. 2017. Verb morphological generator for telugu. Indian Journal of Science and Technology, 10:13. ↗
11. Roald Eiselen and Tanja Gaustad. 2023. Deep learning and low-resource languages: How much data is enough? a case study of three linguistically distinct south african languages. In Proceedings of the Fourth workshop on Resources for African Indigenous Languages (RAIL 2023), pages 42–53. ↗
12. Fitsum Gaim, Wonsuk Yang, and Jong C Park. 2022. Geezswitch: Language identification in typologically related low-resourced east african languages. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 6578–6584. find
13. Madhavi Ganapathiraju and Lori Levin. 2006. Telmore: Morphological generator for telugu nouns and verbs. In Proceedings of the Second International Conference on Digital Libraries. find
14. Michael Gasser. 2011. Hornmorpho: a system for morphological processing of amharic, oromo, and tigrinya. In Conference on Human Language Technology for Development, Alexandria, Egypt, pages 94–99. find
15. Michael Gasser. 2012. Hornmorpho 2.5 user’s guide. Indiana University, Indiana. find
16. Alicia González Martínez, Susana López Hervás, Doaa Samy, Carlos G Arques, and Antonio Moreno Sandoval. 2013. Jabalín: a comprehensive computational model of modern standard arabic verbal morphology based on traditional arabic prosody. In Systems and Frameworks for Computational Morphology: Third International Workshop, SFCM 2013, Berlin, Germany, September 6, 2013 Proceedings 3, pages 35–52. Springer. ↗ our card
17. Alicia González Martínez, Susana López Hervás, Doaa Samy, Carlos G. Arques, and Antonio Moreno Sandoval. 2013. Jabalín: A comprehensive computational model of modern standard arabic verbal morphology based on traditional arabic prosody. In Systems and Frameworks for Computational Morphology, pages 35– 52, Berlin, Heidelberg. Springer Berlin Heidelberg. ↗ our card
18. Vishal Goyal and Gurpreet Singh Lehal. 2008. Hindi morphological analyzer and generator. In 2008 First International Conference on Emerging Trends in Engineering and Technology, pages 1156–1159. IEEE. find
19. B. Hailay. 2013. Design and development of tigrigna search engine. A thesis Submitted to School of Graduate Studies of addis ababa University in Partial fulfillment for the Degree of Master of Science in Computer Science. find
20. Levon Haroutunian. 2022. Ethical considerations for low-resourced machine translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 44–54. find
21. Dimitar Kazakov and Suresh Manandhar. 2001. Unsupervised learning of word segmentation rules with genetic algorithms and inductive logic programming. Machine Learning, 43:121–162. ↗
22. Mikhail Korobov. 2015. Morphological analyzer and generator for russian and ukrainian languages. In Analysis of Images, Social Networks and Texts: 4th International Conference, AIST 2015, Yekaterinburg, Russia, April 9–11, 2015, Revised Selected Papers 4, pages 320– 332. Springer. ↗
23. Kimmo Koskenniemi. 1983. Two-level morphology: A general computational model for wordform recognition and production. University of Helsinki. Department of General Linguistics. find
24. Kimmo Koskenniemi. 1984. A general computational model for word-form recognition and production. In 10th International Conference on Computational Linguistics and 22nd Annual Meeting of the Association for Computational Linguistics. The Association for Computational Linguistics. find
25. Thomas O. Lambdin. 1978. Introduction to Classical Ethiopic (Ge’ez). Harvard Semitic Studies - HSS 24. find
26. K Lisanu. 2002. Design and development of automatic morphological synthesizer for Amharic perfective verb forms. Ph.D. thesis, Master’s thesis, school of Information Studies for Africa, Addis Ababa. find
27. Stephen G Pulman, Graham J RUSSELL, Graeme D Ritchie, and Alan W Black. 1988. Computational morphology of english. ↗
28. SK Saranya. 2008. Morphological analyzer for malayalam verbs. Unpublished M. Tech Thesis, Amrita School of Engineering, Coimbatore. find
29. Gabriella F Scelta and Pilar Quezzaire-Belle. 2001. The comparative origin and usage of the ge’ez writing system of ethiopia. Unpublished manuscript, Boston University, Boston. Retrieved July, 25:2009. find
30. Khaled Shaalan, Azza Abdel Monem, and Ahmed Rafea. 2007. Arabic morphological generation from interlingua: A rule-based approach. In Intelligent Information Processing III: IFIP TC12 International Conference on Intelligent Information Processing (IIP 2006), September 20–23, Adelaide, Australia 3, pages 441–451. Springer. find
31. Khaled Shaalan et al. 2010. Rule-based approach in arabic natural language processing. The International Journal on Information and Communication Technologies (IJICT), 3(3):11–19. find
32. Muluken Andualem Siferew. 2013. Comparative classification of Ge’ez verbs in the three traditional schools of the Ethiopian Orthodox Church, volume 17 of Semitica et Semitohamitica Berolinensia. Shaker Verlag, Aachen. find
33. R Sunil, Nimtha Manohar, V Jayan, and KG Sulochana. 2012. Morphological analysis and synthesis of verbs in malayalam. ICTAM-2012. find
34. Shuly Wintner. 2014. Morphological processing of semitic languages. In Natural language processing of Semitic languages, pages 43–66. Springer. ↗
35. A. Zeradawit. 2017. ልሳናተ ሴም, 1st edition. ትንሳኤ ማተምያ ድርጅት, Addis Ababa, Ethiopia. Results obtained by the experimentation of the system prototype find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/aclbulk-2024-gidey-morphological-synthesizer-ge-ez-language/