%0 Conference Paper %1 LREC18_Xhosa_Dataset %A Bosch, Sonja %A Eckart, Thomas %A Klimek, Bettina %A Goldhahn, Dirk %A Quasthoff, Uwe %B 11th edition of the Language Resources and Evaluation Conference, 7-12 May 2018, Miyazaki, Japan %D 2018 %K aligned aligned-project group_aksw kilt kilt_publications klimek mmoon sdw %T Preparation and Usage of Xhosa Lexicographical Data for a Multilingual, Federated Environment %U http://svn.aksw.org/papers/2018/LREC18_Xhosa_Dataset/public.pdf %X The South African linguistic landscape is characterised by multilingualism and the influence between their eleven official and some local languages. Unfortunately, for most of the languages the amount and quality of available lexicographical data is suboptimal, even though its availability is essential for all educational institutions and for the development of state-of-the-art language technology. In this paper we present a new source of lexicographical data for Xhosa, a language spoken by more than eight million speakers. For its utilisation in a multilingual and federated environment it is modelled using a dedicated OWL ontology for Bantu languages and possesses all features that are currently considered integral for the promotion of resource reuse as well as long-term usage. In the future, the introduced ontology may be used for other Bantu languages as well and may ease their combination to achieve more extensive, multilingual data stocks.

@inproceedings{LREC18_Xhosa_Dataset, abstract = {The South African linguistic landscape is characterised by multilingualism and the influence between their eleven official and some local languages. Unfortunately, for most of the languages the amount and quality of available lexicographical data is suboptimal, even though its availability is essential for all educational institutions and for the development of state-of-the-art language technology. In this paper we present a new source of lexicographical data for Xhosa, a language spoken by more than eight million speakers. For its utilisation in a multilingual and federated environment it is modelled using a dedicated OWL ontology for Bantu languages and possesses all features that are currently considered integral for the promotion of resource reuse as well as long-term usage. In the future, the introduced ontology may be used for other Bantu languages as well and may ease their combination to achieve more extensive, multilingual data stocks.}, added-at = {2024-03-04T14:13:51.000+0100}, author = {Bosch, Sonja and Eckart, Thomas and Klimek, Bettina and Goldhahn, Dirk and Quasthoff, Uwe}, biburl = {https://www.bibsonomy.org/bibtex/28a6f80ec179f6b235206e3f9967d168d/aksw}, booktitle = {11th edition of the Language Resources and Evaluation Conference, 7-12 May 2018, Miyazaki, Japan}, interhash = {686a8803c2991699c7c8cfeccc074c63}, intrahash = {8a6f80ec179f6b235206e3f9967d168d}, keywords = {aligned aligned-project group_aksw kilt kilt_publications klimek mmoon sdw}, owner = {Bettina}, timestamp = {2024-03-04T14:13:51.000+0100}, title = {Preparation and Usage of Xhosa Lexicographical Data for a Multilingual, Federated Environment}, url = {http://svn.aksw.org/papers/2018/LREC18_Xhosa_Dataset/public.pdf}, year = 2018 }