Abstract
Because a large portion of population in rural areas in sub Saharan Africa understand only local languages, they do not have access all to content available in the World Wide Web. Most content are available in English, Spanish, French, etc. Content in low-resource languages such as Wolof, which is mostly spoken in Senegal, are scarce. Automatic systems for natural language understanding such as machine translation systems that can transform information from common to low-resource languages would allow people in rural areas to access relevant scientific or health content.
Nowadays, word representation is the preliminary step of natural language understanding models. This paper presents investigations we conducted to build Wolof words representation using a corpus gathered from Internet. We applied neural word embedding models to the Wolof language corpus. These models are known to be able to capture into the embedding space semantic an syntactic relations between words. Experiments we conducted suggest that, despite a limited corpus size, our models successfully captures relations between words.
Authors thank the CEA MITIC for funding this work.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
AAI State of Education in Africa Report 2015. http://www.aaionline.org/wp-content/uploads/2015/09/AAI-SOE-report-2015-final.pdf
Bengio, Y., Ducharme, R., Vincent, P., Janvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 1137–1155 (2003)
Collobert, R., Weston, J.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the ICML (2008)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: ICLR (2013)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS (2013b)
Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: EMNLP (2014)
Arora, S., Li, Y., Liang, Y., Ma, T., Risteski, A.: A latent variable model approach to PMI-based word embeddings. Trans. ACL 4, 385–399 (2016)
Dione, C.B.: LFG parse disambiguation for Wolof. J. Lang. Model. 2(1), 105–165 (2014)
Dione, C.B.: Valency change and complex predicates in Wolof: an LFG account. In: LFG Conference (2013)
Dione C.B.: An LFG approach to Wolof cleft constructions. In: LFG Conference (2012)
Khoule, M., Thiam, M.N., Nguer, E.M.: Towards the establishment of a LMF-based Wolof language lexicon. Traitement Automatique des Langues Africaines (TALAf) (2014)
Pauw, G.D., Wagacha, P.W., de Schryver, G.-M.: Towards English - Swahili machine translation. In: Research Workshop of the Israel Science Foundation (2011)
Ombui, E.O., Wagacha, P.W., Ng’ang’a, W.: InterlinguaPlus machine translation approach for under-resourced languages: Ekegusii & Swahili. In: Workshop on the Use of Computational Methods in the Study of Endangered Languages (2014)
Gebreegziabher, M., Besacier, L.: English-Amharic statistical machine translation. In: Workshop on Spoken Language Technologies for Under-Resourced Languages (2012)
Sichel, H.S.: On a distribution law for word frequencies. J. Am. Stat. Assoc. 70, 542–547 (1975)
Pathe, D.: Grammaire de wolof moderne, Edition Presence Africaine (1971)
Cisse, M.T., Diagne, A.M., Campenhoudt, M.V., Muraille, P.: Mise au point d’une base de données lexicale multifonctionnelle : le dictionnaire unilingue wolof et bilingue wolof-français. Journées LC (2007)
Young, T., Hazarika, D., Poria, S., Cambria, E.: Recent trends in deep learning based natural language processing. arXiv:1708.02709 (2018)
Wild, F., Stahl, C.: Investigating unstructured texts with latent semantic analysis. In: Decker, R., Lenz, H.-J. (eds.) Advances in Data Analysis. SCDAKO, pp. 383–390. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-70981-7_43
Ba, M.: So long a letter. Nouvelles Editions Africaines. https://en.wikipedia.org/wiki/So_Long_a_Letter (1979)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Lo, A., Dione, C.M.B., Nguer, E.M., Ba, S.O., Lo, M. (2020). Building Word Representations for Wolof Using Neural Networks. In: Thorn, J., Gueye, A., Hejnowicz, A. (eds) Innovations and Interdisciplinary Solutions for Underserved Areas. InterSol 2020. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 321. Springer, Cham. https://doi.org/10.1007/978-3-030-51051-0_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-51051-0_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-51050-3
Online ISBN: 978-3-030-51051-0
eBook Packages: Computer ScienceComputer Science (R0)