Setswana Tokenisation and Computational Verb Morphology: Facing the Challenge of a Disjunctive Orthography

Prefixes of the Setswana verb • The subject agreement morphemes, written disjunctively, include non-consecutive subject agreement morphemes and consecutive subject agreement morphemes. For example, the non-consecutive subject agreement morpheme for class 5 is le as in lekau le a tshega (the young man is laughing), while the consecutive subject agreement morpheme for class 5 is la as in lekau la tshega (the young man then laughed). • The object agreement morpheme is written disjunctively in most instances, for example ba di bona (they see it). • The reflexive morpheme i(-self) is always written conjunctively to the root, for example o ipona (he sees himself). • The aspectual morphemes are written disjunctively and include the present tense morpheme a, the progressive morpheme sa (still) and the potential morpheme ka (can). Examples are o a araba (he answers), ba sa ithuta (they are still learning) and ba ka ithuta (they can learn). • The temporal morpheme tla (indicating the future tense) is written disjunctively, for example ba tla ithuta (they shall learn). • The negative morphemes ga, sa and se are written disjunctively. Examples are ga ba ithute (they do not learn), re sa mo thuse (we do not help him), o se mo rome (do not send him).