Ukwabelana - An open-source morphological Zulu corpus

Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), pages 1020–1028, Beijing, August 2010 Ukwabelana - An open-source morphological Zulu corpus Sebastian Spiegler Intelligent Systems Group University of Bristol spiegler@cs.bris.ac.uk Andrew van der Spuy Linguistics Department University of the Witwatersrand andrew.vanderspuy@wits.ac.za Peter A. Flach Intelligent Systems Group University of Bristol peter.flach@bris.ac.uk Abstract Zulu is an indigenous language of South Africa, and one of the eleven official languages of that country. It is spoken by about 11 million speakers. Although it is similar in size to some Western languages, e.g. Swedish, it is consid- erably under-resourced. This paper presents a new open-source morphologi- cal corpus for Zulu named Ukwabelana corpus. We describe the agglutinating morphology of Zulu with its multiple prefixation and suffixation, and also introduce our labeling scheme. Further, the annotation process is described and all single resources are explained. These comprise a list of 10,000 labeled and 100,000 unlabeled word types, 3,000 part-of-speech (POS) tagged and 30,000 raw sentences as well as a morphological Zulu grammar, and a parsing algorithm which hypothesizes possible word roots and enumerates parses that conform to the Zulu grammar. We also provide a POS tagger which assigns the grammatical category to a morphologically analyzed word type. As it is hoped that the corpus and all resources will be of benefit to any person doing research on Zulu or on computer-aided analysis of languages, they will be made available in the public domain from http://www.cs.bris. ac.uk/Research/MachineLearning/ Morphology/Resources/. 1 Introduction Zulu (also known as isiZulu) is a Bantu language of South Africa, classified as S.30 in Guthrie’s classification scheme (Guthrie, 1971). Since 1994, it has been recognized as one of the eleven official languages of South Africa. It has a written history of about 150 years: the first grammar was published by Grout (1859), and the first dictionary by Colenso (1905). There are about 11 million mother-tongue speakers, who constitute approxi- mately 23% of South Africa’s population, making Zulu the country’s largest language. Zulu is highly mutually intelligible with the Xhosa, Swati and Southern Ndebele languages, and with Ndebele of Zimbabwe (Lanham, 1960), to the extent that all of these can be consid- ered dialects or varieties of a single language, Nguni. Despite its size, Zulu is considerably under-resourced, compared to Western languages with similar numbers of speakers, e.g. Swedish. There are only about four regular publications in Zulu, there are few published books, and the lan- guage is not used as a medium of instruction. This of course is partly due to the short time- span of its written history, but the main reason, of course, is the apartheid history of South Africa: for most of the twentieth century resources were allocated to Afrikaans and English, the two former official languages, and relatively few resources to the indigenous Bantu languages. Since 1994, Zulu has had a much larger presence in the media, with several television programs being broadcast in Zulu every day. Yet much needs to be done in order to improve the …

Content truncated to 500 words