Abstract
Computational studies of Igbo language are constrained by non-availability of large electronic corpora of Igbo text, a prerequisite for data-driven morphological induction. Existing unsupervised models, which are frequent-segment based, do not sufficiently address non-concatenative morphology and cascaded affixation prevalent in Igbo morphology , as well achieving affix labelling. This study devised a data-driven model that could induce non-concatenative aspects of Igbo morphology , cascaded affixation and affix labelling using frequent pattern-based induction . Ten-fold Cross Validation (TCV) test was used to validate the propositions using percentages. An average accuracy measure of 88% was returned for the developed model. Ten purposively selected Igbo first speakers also evaluated samples of 100 model-analysed words each and the mean accuracy score of 82% was recorded. We conclude that morphology induction can be realized with a modestly sized corpus, demonstrating that electronic corpora scarcity does not constrain computational morphology studies as it would other higher levels of linguistic analysis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
O. Awobuliyi, Eko Iseda-Oro Yoruba (Montem Paper Backs, Akure, Ondo state, 2008)
K.R. Beesley, L. Karttunen, Finite State Morphology (CSLI Publications, Stanford, United States of America, 2003)
R. Blench, Atlas of Nigerian languages, 3rd edn. (2012) Retrieved from 9 June 2015, www.rogerblench.info/Language/Africa/Nigeria/Atlas%20of%20Nigerian%20Languages-%20ed%20III.pdf
M. Creutz, Induction of the morphology of natural language: unsupervised morpheme segmentation with application to automatic speech recognition. Ph.D. Thesis, Computer and Information Science Department, Helsinki, University of Technology, Espoo (2007), xi+110 pp.
G. De Pauw, G. De Schryver, Improving the computational morphological analysis of a Swahili corpus for lexicographic purposes. Lexikos Afr. Assoc. Lexicogr. (AFRILEX)-reeks Series 18, 303–318 (2008)
N. Emenanjo, The interfix: an aspect of universal morphology. J. West Afr. Lang. XII 1(1982), 77–88 (1982)
N. Emenanjo, Elements of Modern Igbo Grammar (University Press Limited (UPL), Ibadan, 1987)
M.A. Fullwood, T.J. O’Donnell, Learning non-concatenative morphology, in Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, 8 August 2013, Sofia, Bulgaria, pp. 21–27
Gale Group Inc., Igbo. Junior Worldmark Encyclopedia of World Cultures (1999). Retrieved from 10 August 2010, Encyclopedia.com: http://www.encyclopedia.com/doc/1G2-3435900354.html
J. Goldsmith, Unsupervised learning of the morphology of a natural language. Mass. Inst. Technol. (MIT) Press J. 27(2), 153–198 (2001). https://doi.org/10.1162/089120101750300490
J. Goldsmith, An algorithm for the unsupervised learning of morphology. Nat. Lang. Eng. 1(1) (2005). Cambridge University Press. Retrieved from, http://hum.uchicago.edu/~jagoldsm/Papers/algorithm.pdf
H. Hammarström, Unsupervised learning of morphology and the languages of the world, Doctoral thesis, Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Sweden (2009), 284 pp.
H. Hammarström, L. Borin, Unsupervised learning of morphology. MIT Press J. 37(2), 309–350 (2010)
Z. Harris, Morpheme Boundaries within Words: Report on a Computer Test. Transformations and Discourse Analysis Papers (1967), p. 73
O.U. Iheanetu, Data-driven model of Igbo morphology. Doctoral thesis, Africa Regional Centre for Information Science, (ARCIS), University of Ibadan, Nigeria (2015) 284 pp.
O.U. Iheanetu, O. Oha, Some salient issues in the unsupervised learning of Igbo morphology, in World Congress on Engineering and Computer Science 2017. Lecture Notes in Engineering and Computer Science, 25–27 October 2017, San Francisco, USA, pp. 389–393
P. Lambert, M. Costa-jussa, R.E. Banchas, Introduction, in Workshop on Creating Cross-Language Resources for Disconnected Languages and Styles, 27th May 2012. Istanbul, Turkey (2012)
J.J. McCarthy, A prosodic theory of nonconcatenative morphology. Linguist. Inq. 12(3), 373–418 (1981)
P. MacClanahan, G. Busby, R. Haertel, K. Heal, D. Lonsdale, K. Seppi, E. Ringer, A probabilistic morphological analyser for Syriac, in Proceedings of the Conference on Empirical Methods in Natural Language Processing (2010), pp. 810–820
B.M. Mba, A Minimalist Theory and Application to Igbo (Catholic Institute for Development Justice and Peace (CIDJAP) Press, Enugu, 2011)
B.M. Mba, Circumfixation: interface of morphology and syntax in Igbo derivational morphology. IOSR J. Humanit. Soc. Sci. (JHSS) 5(6), 1–8 (2012)
O.M. Ndimele, A First Course on Morphology and Syntax (Emhai Printing and Publishing Company, Port Harcourt, 1999)
B.I.N. Osuagwu, G.I. Nwaozuzu, G.A. Dike, V.N. Nwaogu, L.C. Okoro, Fundamentals of linguistics (Colon Concept Ltd, Owerri, 1997)
L.M. Paul, G.F. Simons, C.D. Fennig (eds.), Ethnologue: Languages of the World, Eighteenth Edition (SIL International, Dallas, Texas, 2015). Retrieved from 20 June 2015, http://www.ethnologue.com/language/ibo
A.K. Simpson, The origin and development of nonconcatenative morphology. Ph.D. Thesis. Graduate Division of the Department of California (2009), 194 pp.
University of California, Los Angeles (UCLA) Language Materials Project 2009. Igbo. UCLA Language Materials Project. Retrieved from 20 October 2010, http://www.lmp.ucla.edu/Profile.aspx?LangID=13&menu=004
V.N. Vapnik, An overview of statistical learning theory. IEEE Trans. Neural Netw. 10(5), 988–999 (1999)
Acknowledgements
I acknowledge the entire management and staff of Covenant University, Ota, Nigeria for financing the publication of this material.
The tests and results presented here are those contained in an unpublished thesis of Iheanetu (2015). I acknowledge all my supervisors for their immense contributions to this study.
The Catholic Arch Bishop of Owerri, His Grace, Dr. Amarachi Obinna is highly appreciated for the release and permission to use electronic prints of Odenigbo lecture series. Finally, I acknowledge the management and staff of Africana-Fep publishers for the permission to use Baibụl Nsọ Nhazi Katọlik for the purposes of this study.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Iheanetu, O.U., Oha, O. (2019). Addressing the Challenges of Igbo Computational Morphological Studies Using Frequent Pattern-Based Induction. In: Ao, SI., Kim, H., Amouzegar, M. (eds) Transactions on Engineering Technologies. WCECS 2017. Springer, Singapore. https://doi.org/10.1007/978-981-13-2191-7_11
Download citation
DOI: https://doi.org/10.1007/978-981-13-2191-7_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-2190-0
Online ISBN: 978-981-13-2191-7
eBook Packages: EngineeringEngineering (R0)