Containing overgeneration in Zulu computational  morphology

Bosch, Sonja E.; Pretorius, Laurette

dc.contributor.author	Bosch, Sonja E.
dc.contributor.author	Pretorius, Laurette
dc.date.accessioned	2016-09-30T13:32:42Z
dc.date.available	2016-09-30T13:32:42Z
dc.date.issued	2008
dc.identifier.citation	Pretorius, Laurette & Sonja Bosch. 2008. Containing overgeneration in Zulu computational morphology. Southern African Linguistics and Applied Language Studies 26(2): 209–216.	en
dc.identifier.issn	1607-3614
dc.identifier.uri	http://hdl.handle.net/10500/21587
dc.description.abstract	The development of a large-coverage, computational morphological analyser for Zulu requires the modelling not only of the regular phenomena often associated with word formation, but also the idiosyncratic behaviour that may occur in Zulu morphology. This paper discusses the application of an existing rule-based, finite-state morphological analyser prototype ZulMorph in semi-automating the mining of available Zulu language corpora for idiosyncratic behaviour. The semi-automated procedure makes provision for bootstrapping the morphological analyser to include newly extracted information from corpora. Of particular interest is also the central role that the machine-readable lexicon plays. The procedure is applied to a Zulu development corpus of 30 000 types and the results are given and discussed.	en
dc.language.iso	en	en
dc.relation.ispartofseries	Southern African Linguistics and Applied Language Studies;26(2)
dc.rights	Copyright © NISC Pty Ltd.
dc.title	Containing overgeneration in Zulu computational morphology	en
dc.type	Article	en
dc.description.department	African Languages	en